diff --git a/.gitattributes b/.gitattributes deleted file mode 100644 index eef5d65ff2bbfd6b8f188963069cfd3d8b6e4e66..0000000000000000000000000000000000000000 --- a/.gitattributes +++ /dev/null @@ -1,111 +0,0 @@ -*.7z filter=lfs diff=lfs merge=lfs -text -*.arrow filter=lfs diff=lfs merge=lfs -text -*.bin filter=lfs diff=lfs merge=lfs -text -*.bz2 filter=lfs diff=lfs merge=lfs -text -*.ckpt filter=lfs diff=lfs merge=lfs -text -*.ftz filter=lfs diff=lfs merge=lfs -text -*.gz filter=lfs diff=lfs merge=lfs -text -*.h5 filter=lfs diff=lfs merge=lfs -text -*.joblib filter=lfs diff=lfs merge=lfs -text -*.lfs.* filter=lfs diff=lfs merge=lfs -text -*.mlmodel filter=lfs diff=lfs merge=lfs -text -*.model filter=lfs diff=lfs merge=lfs -text -*.msgpack filter=lfs diff=lfs merge=lfs -text -*.npy filter=lfs diff=lfs merge=lfs -text -*.npz filter=lfs diff=lfs merge=lfs -text -*.onnx filter=lfs diff=lfs merge=lfs -text -*.ot filter=lfs diff=lfs merge=lfs -text -*.parquet filter=lfs diff=lfs merge=lfs -text -*.pb filter=lfs diff=lfs merge=lfs -text -*.pickle filter=lfs diff=lfs merge=lfs -text -*.pkl filter=lfs diff=lfs merge=lfs -text -*.pt filter=lfs diff=lfs merge=lfs -text -*.pth filter=lfs diff=lfs merge=lfs -text -*.rar filter=lfs diff=lfs merge=lfs -text -*.safetensors filter=lfs diff=lfs merge=lfs -text -saved_model/**/* filter=lfs diff=lfs merge=lfs -text -*.tar.* filter=lfs diff=lfs merge=lfs -text -*.tar filter=lfs diff=lfs merge=lfs -text -*.tflite filter=lfs diff=lfs merge=lfs -text -*.tgz filter=lfs diff=lfs merge=lfs -text -*.wasm filter=lfs diff=lfs merge=lfs -text -*.xz filter=lfs diff=lfs merge=lfs -text -*.zip filter=lfs diff=lfs merge=lfs -text -*.zst filter=lfs diff=lfs merge=lfs -text -*tfevents* filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-20000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-100000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-phase2/hf/step-670000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-phase2/hf/step-680000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-phase2/hf/step-690000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-phase2/hf/step-700000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-phase2/hf/step-710000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-phase2/hf/step-720000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-phase2/hf/step-730000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-phase3/hf/step-740000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-phase3/hf/step-760000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-phase3/hf/step-780000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-phase3/hf/step-800000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-phase3/hf/step-819999/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/tokenizer.json filter=lfs diff=lfs merge=lfs -text -checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-100000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-100000/model-00001-of-00004.safetensors deleted file mode 100644 index 21f094b9317bca426942d0a8d0b7305e7e14781f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-100000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:17f4d5c376aeb0d8e03b76bd0430ac3bcc71851a82d3632829166f9897575090 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-100000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-100000/model-00002-of-00004.safetensors deleted file mode 100644 index df99f9c893d46990f7f6f87db1f511b7ba914d36..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-100000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8b7f5bfeac4b4f54a1ec3d3f007127f1ddcc9367bf364d05daba5448ce67411f -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-100000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-100000/model-00003-of-00004.safetensors deleted file mode 100644 index 6a378fc6fc3f131fdd4932160858bb13e3b85ae4..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-100000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:05cf77e02cc672dc27e1b22dad019c8b77736bc756c1ae060880b452af6ffccd -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-100000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-100000/model-00004-of-00004.safetensors deleted file mode 100644 index 12b8f37c3cbb5aaa188482757010967c6e265aad..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-100000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:66c4a40a176221fad2f41c2c4386cbc6e7738b0896e6b7b8196ea0ad25eb2fbe -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/model-00001-of-00004.safetensors deleted file mode 100644 index 7f18f5a90ff323b36927f31fa31f0864875ac163..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:01ad23569b1b62dc1e49c717bb3588675565283d535380292abb0c233d0ddc6b -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/model-00002-of-00004.safetensors deleted file mode 100644 index aad648e6c35a1930f494580143d187175a2cb263..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4be9ba37b5d444bf571be55a50b4ad1db53049a448d318b180793d5989da51c0 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/model-00003-of-00004.safetensors deleted file mode 100644 index 4d0355ed55e89810f9edc486acb681b5712bd00e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:47646ad793a34c18e63c3f0b9448e9f28d585fe144e149d90184b90710cd910a -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/model-00004-of-00004.safetensors deleted file mode 100644 index 11b16062d1208c2ee82ffdb56a62cf8ba5160cd5..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:67172c0af121a45033a624c073a6568710c102c55ffa39eb1b18f8d26a4351e0 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-120000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/model-00001-of-00004.safetensors deleted file mode 100644 index 37ac99bdc7df86261b03bc029f5a7b42d1be5828..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:cf8f63625eab7d79884b5eb770750c7deca2b2dc4260a3eda4c0db0fe1f8065b -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/model-00002-of-00004.safetensors deleted file mode 100644 index aa2f8733689f3752c928c07242eee0365e9a2575..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:01524993558467c3c8890c3cdc8c83f04132aa9f17be992720cee389a4c733d3 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/model-00003-of-00004.safetensors deleted file mode 100644 index 6145c31a0c79e72bab3e2f28f9140995ddde7a82..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1849c4a3de9eb899597debd12617b1299d452832b9bee39af9d6bb84db4ae3b3 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/model-00004-of-00004.safetensors deleted file mode 100644 index 1508e4e9ab1eca02a3ce13c747d2175485abc656..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e8602b7fb73a4ed8d680a080be2cfcca56f9a9d8b2534f3ab774b40354dd332a -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-140000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/model-00001-of-00004.safetensors deleted file mode 100644 index c568b6af505d7ccd7dc52ec1cb0e7fd7a9ae65d6..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b311cfbb08382df3f65454ee6fd3d97fe98e11b2524fb72f9ffc1fd3a08c41a4 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/model-00002-of-00004.safetensors deleted file mode 100644 index ce348166311a264318bcf9145092d53dc9186fcd..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:74d67a15ce15ad3333366195f36ca8fca30bd4407ef5b23687a909913b86f17b -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/model-00003-of-00004.safetensors deleted file mode 100644 index 09b5a612be91d47a47a3dfdbef9c09f01021790d..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2c9e6893691a7f03c16d8de548483c20e829fcf660b56e1e1c2f986319bb9859 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/model-00004-of-00004.safetensors deleted file mode 100644 index b9e5a429afc6b42328083f0f5759c4a7399ac518..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8193b491a9524aba82d3ffb0fef138447087a8bc81ed9473e8d6f3e004d44ca3 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-160000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/model-00001-of-00004.safetensors deleted file mode 100644 index 9342020fb1254b12eedd9d9d9caaf0cc936eb644..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4789eac86f9965508436166ed66f7b985fc4adf96c79931984d1ffed0ad1453e -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/model-00002-of-00004.safetensors deleted file mode 100644 index 1bcdfae54c8e29ce2e07b4911cfcdcafe00e62f2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6e145a23ba69e0591082bc2a23df9b6adda549e56eeea4eb37bd7d37980c9657 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/model-00003-of-00004.safetensors deleted file mode 100644 index 433784719c8e639f3c45ae4e62370bc41dac007c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0ea434e6c2fa7ca5ab0413f58a1cf10d8291062188327aa7d57ceec0ea4f9d0a -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/model-00004-of-00004.safetensors deleted file mode 100644 index 08b4b911816a81a51ffad0c1db5d69765a20ba0a..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4b45a6ab2fb87aa1434d7ffd485c3519f210c4b79b3a186dd8e9496807e258eb -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-180000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-20000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-20000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-20000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-20000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-20000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-20000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-20000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-20000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-20000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-20000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-20000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-20000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-20000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-20000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-20000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/model-00001-of-00004.safetensors deleted file mode 100644 index a495187f93a83e9bbea426bcf6af062ccf2487ba..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5bde80b6a9ce15a91bd570ef4d2f7755b837b92dcb3b337a07c62af5460bdb45 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/model-00002-of-00004.safetensors deleted file mode 100644 index 1e8bcd39e52ac3a7b1755f65c962acf60dc403d5..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c67929da23bf8f1340c3e0d2d74ae07f3f1cfa459b5fab48c51b99b5c5bf630e -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/model-00003-of-00004.safetensors deleted file mode 100644 index a789cf31399e058621e48d60a9471da6b015e722..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c4d0c46e80f117b8f6fe96ff8ae6f0da0097a095f581aac24c6b5b57058f28db -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/model-00004-of-00004.safetensors deleted file mode 100644 index f48fd15cfb499ad8fd2dfde98441036216bc0e2e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8c88a3d1558050ec4b849dd05c669832d0586375c325c6f9974663501630eb28 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-200000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/model-00001-of-00004.safetensors deleted file mode 100644 index 3c0b42d65807450435317eab71119524f37bbe97..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f37767b30fc18b3b0a560027973b82a45f1143f666e6cab2a034576260477729 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/model-00002-of-00004.safetensors deleted file mode 100644 index c81147deb9a08a7141fff9a4ee346fd7e1b3a091..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6f9b45f994960d746e8f59113f09d3e68a1533074a228602ebe7d1bfaa4971f6 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/model-00003-of-00004.safetensors deleted file mode 100644 index 733789c7e21851936d236b74443b3c8015688fa4..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1a5e7d39518c1b6f7e776bdb3a967b4e788c1b27a51f98a4c2f7ed46640ec63f -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/model-00004-of-00004.safetensors deleted file mode 100644 index 3325e743fe1018cdf7d28b855a944598aff3f006..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:46c114ee17359ab582f5fbc621856285279603632fec22f1ef4f727321c20a97 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-220000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/model-00001-of-00004.safetensors deleted file mode 100644 index 0589f45bd3b5e7730882a1c5c5fd276db3cc8cf4..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3acb20b31490d57c68a607876d8a4e6383048d3e5041b48ad3493dd0dd8b6fab -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/model-00002-of-00004.safetensors deleted file mode 100644 index 03348f052f2a0ed77a68e29510b21024b5e6f368..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b907f300ea3e48f72fc18d7dab256e2a3f3d46a10d43542f2b3d647e87fa7ff8 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/model-00003-of-00004.safetensors deleted file mode 100644 index ec50c9a8d0eaba95e9fae0cf9bda7041a089742e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:da23435d90e0f89327e5893e299ed6b15c9609817cb5c642e071db794efa7f4f -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/model-00004-of-00004.safetensors deleted file mode 100644 index bc693e4bee49817d422a31981b8418c318144962..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1e63d2d23d9c5d56699c869f4996cc414d4b82ab91416097d2cabd7966e5298f -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-240000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/model-00001-of-00004.safetensors deleted file mode 100644 index e29ba299299c1006f648b3c256d27c6a6482d044..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d8bb5d3ecc098e31c41c50e0d04ac46b55015e0c9b6eeecee601fc71a00fb55f -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/model-00002-of-00004.safetensors deleted file mode 100644 index 85e455342eec1c7a439c450ad2a14df75e6f44f0..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:02ba3e231d65d0eb3a8055025128fe2024a6829835822671e2c00fd8d49967fd -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/model-00003-of-00004.safetensors deleted file mode 100644 index 8ee0421e5920cdd61cb9256b1d9f01cc9356c24d..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:743c295a412066d00c2b8387238aed4cb637fcbe5b3290e78b1b6a37fd1a2220 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/model-00004-of-00004.safetensors deleted file mode 100644 index ecc30a38cbe2a514aba8e5c6322ab6a590413864..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:333e9442817e5907811db4b1924aebf82e782b541ace7995bb58b6f385bfca71 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-260000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/model-00001-of-00004.safetensors deleted file mode 100644 index 8c9e56e3f9b752d9f13f642208032b29b6c988ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:af61031f8a30a70efcd5a0d6719b00bf6631f7440883203c7da8e470958a8876 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/model-00002-of-00004.safetensors deleted file mode 100644 index 15c2d1b10b00d0313b00140c6ad50072e4455ba8..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4efb34e311c0517b5f3a2a5d96b5c97bd29ec24c8f78e274ea4627ecac684e03 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/model-00003-of-00004.safetensors deleted file mode 100644 index 3552e579ed323ce719400233f248f6b0373e8b8a..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:02a481334d3a59c55d8fa81b2a58e78532975e8d11a6357d90bc5df9d5e0d4c7 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/model-00004-of-00004.safetensors deleted file mode 100644 index 78ab21a5afa68df2c0d7783c9db220fd58b2c046..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3b6ef2b52ea271ca4c13bc9069429c55fd3f8814940da6336d496eff4c5d2043 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-280000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/model-00001-of-00004.safetensors deleted file mode 100644 index 76c2e1d2c99d116b7ce831347c4d4784cc0e8e41..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9373416f3945158fb87d2beee4bd1e681cc2466b161a67073e2c97f7c21a5ee2 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/model-00002-of-00004.safetensors deleted file mode 100644 index 7a000fea0827e6e21dc2601e0c93db556e8cdd05..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1f72177d1c8678aed2e02a9dc77d88d8563ff460682d8c597ab6a8f5f1fde024 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/model-00003-of-00004.safetensors deleted file mode 100644 index 65a76513a80fcd544380f0b5a5153037c7ee6220..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5e27a17c4d7bf54914a863ea479c2c9295b414c2f7eb179644daf9e5222e505a -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/model-00004-of-00004.safetensors deleted file mode 100644 index 682032beef573f2b871640c77ec421b690097fe9..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3bd1e3023d99d8a01a44e28d64eb551526110edb51c6c9f0fee715a0826324ab -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-300000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/model-00001-of-00004.safetensors deleted file mode 100644 index 3f0867eaade9b49b62183e674efe5d55e41f640b..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:683266c54060847cca34393ed83e65fab2800571ec5110bfa6bf8d6850f2e780 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/model-00002-of-00004.safetensors deleted file mode 100644 index 4859204558338d795122acb9f13dbb4d9c0f7469..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e120731e79a585afc949bace7f817f168d9c6f387f1efbc09d5e8d44ef7063b0 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/model-00003-of-00004.safetensors deleted file mode 100644 index 72c83e0b32cc030afeeb072e5b2f78856f8e8ba1..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7b2e32d3e0b21e5e59116dbdc090ca5abb251db54392d85b46eee66e9d14bfa7 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/model-00004-of-00004.safetensors deleted file mode 100644 index d3f7776951966e7210a109c3413d144d095a3737..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:428e6c863e6a938f105e955ca8d9880aafd11251788e8187124a6c0894461e92 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-320000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/model-00001-of-00004.safetensors deleted file mode 100644 index eb6c92f1b1940573e7bb0a6049af96126cd76e6d..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9d5524c83638c5ef82467bc9c072376846ae990ab80c860400126e0b176e33b5 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/model-00002-of-00004.safetensors deleted file mode 100644 index 809322fa4e4e89b8442dcebf12a942e93960786e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d76224df0644b5dc320472854eb6438d8f9ea7886e5cb0fb0e1f5a0370a3183a -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/model-00003-of-00004.safetensors deleted file mode 100644 index 6cb0e6a58f52c69e2ab354aa91bc8963479d9571..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:22961e0f4143ba8f13be4ee7f36f12660e124301a29f1fcabc097f6d865fca55 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/model-00004-of-00004.safetensors deleted file mode 100644 index eb2542b3823a4425d308a55afb35c39338065185..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:042597d73121689f9511dc35a66af3243c82fbc7885715bde7b3f4bb8fe6751a -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-340000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/model-00001-of-00004.safetensors deleted file mode 100644 index 4b823ca85e76d89a79b66fbad2d316b0bcf0d63c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:bc53d3503a5d3bc544246d4ee3c832aa658af3ce102c8c7d86c127909c357d10 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/model-00002-of-00004.safetensors deleted file mode 100644 index c49dd3f74f2c7e9f1dde586ea326b84416e9a786..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ad7dfa2531821f0cb0b4eac6af28832fcd0949a578e25c3c1acb097661be15a9 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/model-00003-of-00004.safetensors deleted file mode 100644 index d2ce0ffd5300e6d0a8eee464a7b516c57ef9d85d..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e908e5e0d23f31bce7ed43504e3e683f3a264a09943e66645953ca320e2e8ada -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/model-00004-of-00004.safetensors deleted file mode 100644 index c837c350102a0cf0f6b5a9e39177f3e3a178b089..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6256c882dcc7aed31832469560fed2766bf54ca79da0fc86ebfbdc704bbed7b2 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-360000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/model-00001-of-00004.safetensors deleted file mode 100644 index 2a64c37615ee80808d34054c28d4a3e98418e911..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:90cd7bf45c049bcf070514396ac5869935e9d9bba337a7cb67c161b7f30f6973 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/model-00002-of-00004.safetensors deleted file mode 100644 index 7d34736567787aa6e3cd44a0f267aec2a532ec11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f7a825c0dbfd5d230a20b3cb8c2f54c7c06c356f485c5e443fb730b0ebd25214 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/model-00003-of-00004.safetensors deleted file mode 100644 index a0a6b8ba1c41f3bff8a3c28d3327a7d30619e735..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:310cdd99b510368d106a1fdd71a80dcf6f331e01593e20f48515e3e8f707c89b -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/model-00004-of-00004.safetensors deleted file mode 100644 index add63a507aa90051435a52c78b2cabd1df9af58d..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:10af31b0c39e8f7665463e537110510dc6746da14265440cf5844f1acb57e37a -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-380000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/model-00001-of-00004.safetensors deleted file mode 100644 index 76f85060f6ef96a23ba8646284b93db32bbb7302..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:551bdd5d614b6027bc8d409cc85c45f0ef6e2f58da19128616e29a4c015faa12 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/model-00002-of-00004.safetensors deleted file mode 100644 index c5a0c1e241050ca332e4a0af4d1d3bdbd2145f0e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6ece1acba5229b9ad5f4d5e6882be4212bcfa0b460fa9cc4746cc2494b04f3d7 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/model-00003-of-00004.safetensors deleted file mode 100644 index 1d9a7d1ab00fcc1de1acf24516496a881488cce2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fc7319c20235e0722a2f46a63c53cad82c09d40034c3ebded6c0861af2f2f5d7 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/model-00004-of-00004.safetensors deleted file mode 100644 index eb6fceff145455d5429c1ad192592a5d64f82e2c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0afecf61dbcdfc85d529c0361f1c1ff24ec2b9935e1d26ddb1d8b2fed5bca1df -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-40000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/model-00001-of-00004.safetensors deleted file mode 100644 index d690aab33d5c2c6ab0b60752cd0299a11288876f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d63d78aeff81f5e3968daed95b6560a96a22c7793ed235de7347c543f7e1747f -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/model-00002-of-00004.safetensors deleted file mode 100644 index 41976bf0578f3ce1db14b9872f461c2a45092062..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b36388a0a17dd60f1e75c6b3a6ace76cafe646191b1ee7fd55ed6a69c05307a1 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/model-00003-of-00004.safetensors deleted file mode 100644 index a0ce855ab26286ee3c1d63eafe3bc202b46b2725..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d7d32a20f8176834912068e981d2ae42543ff415b47c7302c090db469d986807 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/model-00004-of-00004.safetensors deleted file mode 100644 index dc91a0e67ac837baaea8fb196b5fa39a20141ec6..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6584d0aeccce4df225937c00fc76e12fa4f8f223d3d484cd31757a30fda1a864 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-400000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/model-00001-of-00004.safetensors deleted file mode 100644 index 4d0749a194979ecf6750000572cd58bc45181b71..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2c309105b133bbb67840009aa43c6366f890934fd7ec678e9ec8691d822a9341 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/model-00002-of-00004.safetensors deleted file mode 100644 index f996927e66dac987a36b6aee93cd7b278c2cc67e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:16a16baf63a3c42741d963c0aff8a4060189bdb0ea006dd9fd8ecc2b5ac6226f -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/model-00003-of-00004.safetensors deleted file mode 100644 index 90846a9ad6a62c8ac0bd463a5d01288303060666..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5a8254944d72b8cd6e4a03b139e91a620f5365e09131a75b7ba7f92fb2156151 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/model-00004-of-00004.safetensors deleted file mode 100644 index 950f061be705f597d2b671b0b40ad8e9c2b9df33..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:13082f8d64a2b82dea9fe1112fbb7ec0615ebc6d225b9f00fe9687f3a4f5e5bf -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-420000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/model-00001-of-00004.safetensors deleted file mode 100644 index d0a1cbdeeb885eaf7b967f3f5e07839830980189..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ce9e1b4ecd8dd6455e6cd80d6ecefd00b2f2d371f73b049a674d09db9aa9b330 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/model-00002-of-00004.safetensors deleted file mode 100644 index c563d6552c3ae22c23dfde88bf1baf3abb4d3c4e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:15980ce5161c78370e5227fcbd9baed94f2d3f3176bf9416fc094ab8f16fb2de -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/model-00003-of-00004.safetensors deleted file mode 100644 index 6c1ad055661dec484fbfee68c7dec73d91d6cd71..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:eb481d67f1459ea05b8d564b0b6e5c5812daf3b6ef8ba37b9498a02d3c8b7a01 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/model-00004-of-00004.safetensors deleted file mode 100644 index 9eed4b8bb2106cf61ebfbe72571787e508e064cc..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a78d7576ad5b812c36710eeebcaf6e38ac60ed17010e98406269e4076d05dc0a -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-440000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/model-00001-of-00004.safetensors deleted file mode 100644 index 40ae488bd73c5d72b251ea98eb08c228af1d0a7a..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4fa57fca298f181b660a448fdf53ba1e277a967c5e3230ef8b2cbf94e6329bf5 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/model-00002-of-00004.safetensors deleted file mode 100644 index c97f6650649af4b194d8abe4eba7614e6f98b310..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ff986264c8ede76671216d86c6b67a6eec6515c66a26d02ab3adad519e827856 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/model-00003-of-00004.safetensors deleted file mode 100644 index 29931bc4a80e53cae17dc6093fbc11f0537a5c8d..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:26e61f8c491e29e5174220f0df7bcf20b5805b98259e9f7d4414cf25b6ae8e10 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/model-00004-of-00004.safetensors deleted file mode 100644 index 53ae85916b36a1436b9601b623b22d2f20e71e5b..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:591ab8b75b17f839aaa58bab942d257b53809415ef195c87ebc2be9c34065f17 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-460000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/model-00001-of-00004.safetensors deleted file mode 100644 index 434a995700ac38f6f8c1fa2f760ee3e4857b11fa..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b58deb459b78955962c5ea3f998d4abd7ae08a8c82078b5b84d5000b4279a099 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/model-00002-of-00004.safetensors deleted file mode 100644 index bfec80031d78bf09f5b91520e5b96a69af24baa9..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:996d4b465063c8903662bdb3dc9aa91c4db4b10fd6a491f15e6440432bc02e83 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/model-00003-of-00004.safetensors deleted file mode 100644 index 010302b2687de247862fbf9153d406d956a52285..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9be3287f334fc5730bfe6dfbd691f142d40c5c4c078550d8f63c067f0420c7d1 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/model-00004-of-00004.safetensors deleted file mode 100644 index e039e3eaaf7f5f39e84e64dd307d62256f8a5625..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c9a6ecdc3c3ed2b015551a7c68da11b2c1582f8d3403344c10838d02fd2edc1c -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-480000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/model-00001-of-00004.safetensors deleted file mode 100644 index 11e5241e3dd7e01fd2f583ba1f0f368f157cfdcc..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:389c29798029931f6080ee8dcf7e409c8765eb1bc965dc8d69eb403c202bd28d -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/model-00002-of-00004.safetensors deleted file mode 100644 index c8356b04a2d59967746830834aac9d72887b437e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:24e10e1eb5c682130ac86af43311a69337612a20933aecdd67861c355fba8681 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/model-00003-of-00004.safetensors deleted file mode 100644 index 27374a493c4c9e34f5c748db3b6069f5b19d19a8..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b5c9dddcd4157a29c4570818dead550b75442b5c478cc17bb2488e4ab3050ceb -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/model-00004-of-00004.safetensors deleted file mode 100644 index 7f7d8f16d12f59294f8ef149f1b68194f8acbd27..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7fa4248ce294914f92410051719632971bea05197beb94db9d3fae45700f2d6d -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-500000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/model-00001-of-00004.safetensors deleted file mode 100644 index d85c62a43b2e788f848883d6bb1d367b92264eb0..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8073170791904f767c63b70eabd1e001c0d063cfb629a207d433b24c8819021b -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/model-00002-of-00004.safetensors deleted file mode 100644 index 6525d441490ad74a3ded0432f6eb129a42abc50c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ef8a597a90095b5c022da67829c3400a9cabf7f012676287cf9e769af05fe618 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/model-00003-of-00004.safetensors deleted file mode 100644 index 92154d78d64828c2e84b87a4e7c36a985606265a..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7eb9efa65f416d89cf6939809d9bebd342e447808f7b0f95cfc41825efefb3f4 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/model-00004-of-00004.safetensors deleted file mode 100644 index 846c297b4e0c776d13ab723dbec83a069f4584de..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2fea96de60d8eb6bd0d42a3cc02ac96311b0e35d3557e2739037fa16de335aa6 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-520000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/model-00001-of-00004.safetensors deleted file mode 100644 index 9ad1696c9bdd072fa4c75bd48fb3f1df20fd3701..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:88a1f269eb5853b97a510db8c6b120982926853c3fba6317ab5c81154fef3bbc -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/model-00002-of-00004.safetensors deleted file mode 100644 index f525b8da145311e9d2cc66f31320984103b8f7c4..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:cc37f301be10ece3703c95edcb43d43cbefa508f5c493230ea41346fe6477bcf -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/model-00003-of-00004.safetensors deleted file mode 100644 index 6bedff666da8b50b4091cb538d0764beaaf409f1..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e8dfa0ef5f28e22e626c483f286700d2668c543dac49dc7cbfb8fc1d4ddf5e58 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/model-00004-of-00004.safetensors deleted file mode 100644 index c9f992d2b07fbf1b31e6c523b515957d94703b59..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9c254104b8078347b63986554d97e8ebe84faa7f426669834ab3caf57fd42261 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-540000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/model-00001-of-00004.safetensors deleted file mode 100644 index 65cdb2335c471dc0fb90d9869774bd19eba6447e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f2ca076f4610c7a776975879176bb07e502015bcbb66455fa2a5a71ffd6e98cc -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/model-00002-of-00004.safetensors deleted file mode 100644 index e175dfe0628bf5134287602ee7853569d6879d3a..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:eeffeff44a92bbdad5b41226ae234ac9a9ad9b7604cad6ddeb370d0160066f4a -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/model-00003-of-00004.safetensors deleted file mode 100644 index c8e09da03791c8abc99135f15a25284535ee4ed9..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2402948a90120f66b602f3a7367e68fdc64b997370c3925f3a91062ba20326a5 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/model-00004-of-00004.safetensors deleted file mode 100644 index c3feb13bbdf6e1eb6a10e70d89fa84a881147c6c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4a53ae788376331a71245a8d5dca2c07316decfb910790522f41191350533f3d -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-560000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/model-00001-of-00004.safetensors deleted file mode 100644 index e56d83e8c13d6d7f2815aa3a8655bfb9ebd9137a..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:70a25c7092bc61c894734d09e7b637ddfa69acda07b75dc16515e925a775893f -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/model-00002-of-00004.safetensors deleted file mode 100644 index a392afe3eaa1ba3395151801f38e5c1abb1f527a..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7de2aa9547de71e0421d6943c98f040aee1230699867616dcbfcac9b5ffddb47 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/model-00003-of-00004.safetensors deleted file mode 100644 index 68769f9b2dcd28d7456f405a8a1436c8d72afa34..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4c635df6033f15a323f302e7eb5bf3dbb9e9231109fa086a782b3bb7bd6f4a70 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/model-00004-of-00004.safetensors deleted file mode 100644 index 66b7303de808a3be6a110f57d35b4fbdc1b20386..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a47c9d6c293ac8bb3c7243418ba063829b93ed3069aeab9f8e7a224cf490e788 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-580000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/model-00001-of-00004.safetensors deleted file mode 100644 index 759de2ad73170fe7f11891c7d279567cb5e9b624..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e2e41b9d7efb56504388283fb941c948115501d9cbf3c3b812bf4a6de4bc1073 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/model-00002-of-00004.safetensors deleted file mode 100644 index 975ad1a1253cf7131c03bcbe6cfa97c0c9cfca06..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a4745d3cb7a6e49d9db30c61c6ee588428900843436919145efba463a31bb72c -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/model-00003-of-00004.safetensors deleted file mode 100644 index 7e29eb648c0cafad96dc451915a9f7fcfe1793e7..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f7d7e26655e961bf9fda57b01e7e1f70531715a71b20cd69920f5d18d8738445 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/model-00004-of-00004.safetensors deleted file mode 100644 index ad3157d874ed0683784d2afdfafe33c298003efd..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2b0d0e821e3aab0d4e2b8ccef96784868dab7b432e5ab3b1edc8f5311e47437e -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-60000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/model-00001-of-00004.safetensors deleted file mode 100644 index 89700c84bf3283766d957c6b3e60b083ae0824a6..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8c6f20ff5f5f63b54a5a7d4cc09b9d7327eff916cb92379da70159b85e2a9307 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/model-00002-of-00004.safetensors deleted file mode 100644 index f31e1abde70f9a2ac31db0195febfa66b9f6a743..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e8aae02b16531d65608529aca691db22d4b353543aa163c62749281b1a02bc1e -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/model-00003-of-00004.safetensors deleted file mode 100644 index 04cc66bd691fa1bfef2c3ff2567b999e22d2ae5f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:57cdee90509d27f7ce50e10794f0eda641186f478d68036d337cab3644f84529 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/model-00004-of-00004.safetensors deleted file mode 100644 index 70093980c586c6a996faa446b3830356e78dab9e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2c4481a3ede2e08a7a22788f15b745dba5b90a96199ead2f9a7428c776092b5a -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-600000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/model-00001-of-00004.safetensors deleted file mode 100644 index 9a1438d496b5a6da16d58de128f3a7f562ea6079..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9adbd2ac1794c6a88575a73a85fd44d7df62e4360540434b72fcfc5e59a54a7c -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/model-00002-of-00004.safetensors deleted file mode 100644 index 8e15ea9095a3f44573d350c4ac55595994f60997..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:cff977efb37479aaec310d665299895b3f4b8771eec1eb50f115dfe81e3bdf49 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/model-00003-of-00004.safetensors deleted file mode 100644 index 28879a5e823fb2eb5aacee89fef9461e616ccd58..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1ef5e0be5d315d26ee479a446d6987b795a0d8bcc35e43dd2f4f2aeddc874d22 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/model-00004-of-00004.safetensors deleted file mode 100644 index 2536e6ba1f35a9358993eae8b4dfe3eb47932e32..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9e958b5c10b457867ff41e4e45179a4013abdf58bced079d3e6fad73def92435 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-620000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/model-00001-of-00004.safetensors deleted file mode 100644 index 849c22ecfb296ba20ecf50d8b37658ad098ab808..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:90b688b1c68b88de9e4421e5dc911c0893dbb0851d71948018527ac610c22016 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/model-00002-of-00004.safetensors deleted file mode 100644 index 64804e7edc297e225ace200743428876b104ffba..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e6b6bb123d65d25c87027205188a59df3cec0f47f10b59f96d68fc6dab7d2e36 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/model-00003-of-00004.safetensors deleted file mode 100644 index 8a8d31037377b877f7e2f219868ed692cabcb704..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9197f5cbcb3623cfc809c3a297f050ed9baa0e9af61f6385e1b3ce3e660f3549 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/model-00004-of-00004.safetensors deleted file mode 100644 index db07492602690f489957e7ab8a9f37023278f040..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f84c3daca0b87ad1b5bfdf32caaa617c14a83374434c82cdeeffb6fc691a36c1 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-640000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/config.json deleted file mode 100644 index cb9dc42ff4af8a8da61b848065351ae2cdac818e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": null, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/model-00001-of-00004.safetensors deleted file mode 100644 index 1915346794843d5d8e2d16e712baab29e13673a8..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:05dc186bf3ef7de2e109d0a9f5c48d5bea2f51918e1ae68284c79e25ca7b10df -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/model-00002-of-00004.safetensors deleted file mode 100644 index c1e17efa1ada64ee3d605c244a8e6d62c1b85b92..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3bd207ebb641fc2a6374997f48f27fa5a0914e41ead683def80d9a462a2f15b3 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/model-00003-of-00004.safetensors deleted file mode 100644 index 38a8982bf36f66371349f303537f62271201e102..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fb5c4b1476ac64bdaa37c87d7a306167d785a5bcffb3011be270f39f98100389 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/model-00004-of-00004.safetensors deleted file mode 100644 index 2ddd85a81f38fba2f6eab53b5c35972a345c0bd3..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:62f96618574822dfdda7524877b37f6d8fecf2c198190f3d7a77d4a50d68759b -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/special_tokens_map.json deleted file mode 100644 index cfabacc2620186cd3dd4b1dde9a37e057208636e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/special_tokens_map.json +++ /dev/null @@ -1,16 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - } -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/tokenizer_config.json deleted file mode 100644 index cb9ec25536e44d86778b10509d3e5bdca459a5cf..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-660000/tokenizer_config.json +++ /dev/null @@ -1,2061 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/config.json deleted file mode 100644 index 638aa54b51d58c3c572a06d43757b1802bb9ca11..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.46.2", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/model-00001-of-00004.safetensors deleted file mode 100644 index 1a887d16141026b21862479c20e23431b4240acb..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:857620e972daa1b1054eb8201fc3c266f0f028860e3d5c6c6becfbbe9677faeb -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/model-00002-of-00004.safetensors deleted file mode 100644 index d5a8f3c51adaaf532c8187f1b01aed41fa7f3482..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:94c8f70d0a47cadda9a8f3c0a3098a663a1a49329e17cf33591781d5c321cc3c -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/model-00003-of-00004.safetensors deleted file mode 100644 index 323f88dc72dc348864a02e4e3c526b3921408623..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:756b6505e16977c2d051947e867640100663ca75df6e2b7c6d4acc3b1fd1d1cc -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/model-00004-of-00004.safetensors deleted file mode 100644 index 77bf98bd90fed0934c96602dbe49bd4a81e109d3..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:275333bd0c0413870277f2cefb249b6d5474a615329acffab842e52eef394af1 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/tokenizer.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/tokenizer_config.json deleted file mode 100644 index 0df36e82e06f1188c56f572211c39d7d52f1f46e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-80000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/config.json deleted file mode 100644 index 5a697cc5fc70ea77184803009c96b76d35b6862f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": null, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/model-00001-of-00004.safetensors deleted file mode 100644 index 93cd71bba491253cb5b69b9542bcbe0812d71dbc..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d8923c00d9d95459e65b59dc70f0929b5c0329b3f1d2b34db21739d94496542e -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/model-00002-of-00004.safetensors deleted file mode 100644 index 55243cd2c81befbbb83449d2a6888213b5532e19..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:db79ee5ef5ab015cc65c3acf91b33aec9f1e71c56716a23e68e30c41fad9a389 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/model-00003-of-00004.safetensors deleted file mode 100644 index 8bbde37b67b7d04ceff4b81bf7eff77e7daf0e7d..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:92a0679b40dcb59cd4e3d4eaef4c24b4924d6b456884c1a23a5fde620b09e88e -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/model-00004-of-00004.safetensors deleted file mode 100644 index d8c53e7ec700a3f4f4f388831a59520ef6a3e904..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0537ab86230f48e7c026450eb5dfa689d0142885f03f1fb6187eaea84f8c4f43 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/special_tokens_map.json deleted file mode 100644 index cfabacc2620186cd3dd4b1dde9a37e057208636e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/special_tokens_map.json +++ /dev/null @@ -1,16 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - } -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/tokenizer.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/tokenizer_config.json deleted file mode 100644 index 5346f10a1884fed79cfa9e4a40ce7173418b5732..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1020000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/config.json deleted file mode 100644 index c8fb0b04bcf67646ee10a1ae930a7117e2e4cc5c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/model-00001-of-00004.safetensors deleted file mode 100644 index 7219ad1fb87a04f768776be8c09af7139d130d93..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:387fec45f47e96784afbe62e100ffb9daf5f4d02667fe4486765af6518038ff5 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/model-00002-of-00004.safetensors deleted file mode 100644 index 5ebf1b1f9ca2454890fd57b3a8cd073a4f175ff3..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:580d3752646c870e2bd64e3e70e4e823dca844deb3706b15162f73189dd7d36b -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/model-00003-of-00004.safetensors deleted file mode 100644 index c12079a239ab11a93267d9c26ec0f3bce190cd7b..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2e702d20c9573fe7ee640cef9d15f319aadf29324f86e3c5c2470747dbf2b614 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/model-00004-of-00004.safetensors deleted file mode 100644 index 33a521c00867bf788c0a3b8378ed6e610e0ecc75..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:98f13ba5b913f079081fedc5bf6d6cdb4616662a3387fb99d8619e5030a82dbe -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/tokenizer.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/tokenizer_config.json deleted file mode 100644 index 3026161bf4fc56964bad68d35d36b5b815a3f716..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1040000/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/config.json deleted file mode 100644 index c8fb0b04bcf67646ee10a1ae930a7117e2e4cc5c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/model-00001-of-00004.safetensors deleted file mode 100644 index d661323c5181903f702cdc7f488f552c6e8bf724..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fa6428211fa87599eda3e938a598530fcf4e6532c5de1dfc9ac99ad4f647f304 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/model-00002-of-00004.safetensors deleted file mode 100644 index 2f75ac813a9c5570552c20e86cb2759c1f11feef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fb6d4aa476bdc2dfff90f7359466fca91dbc0a61ad85fe6431a4ee362339b5dd -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/model-00003-of-00004.safetensors deleted file mode 100644 index 4d4e8f32e3e7c8046ede646c83cb26a865242391..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ed12e04bc230f622875ff6778f502c677dfdad9d04bc99734c10005299a95ddc -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/model-00004-of-00004.safetensors deleted file mode 100644 index 4460692fc8779d725ac3383ecd76c8e958f7c3ee..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:efaf2c2075e8ca03e80fd9c72a18419d7e7dace1d77b93529661daff9f72be69 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/tokenizer.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/tokenizer_config.json deleted file mode 100644 index 3026161bf4fc56964bad68d35d36b5b815a3f716..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1060000/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/config.json deleted file mode 100644 index 5a697cc5fc70ea77184803009c96b76d35b6862f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": null, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/model-00001-of-00004.safetensors deleted file mode 100644 index a0d847f1b7bbc095adc1c20be4e99d7c919ccdac..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c98be839a88916b79ba75acd23e2244e5fb8635af9d66110bb4d1272febc16b4 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/model-00002-of-00004.safetensors deleted file mode 100644 index df50d4b08d07b0b4d10364c8e331b3bb19c62f3f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c4895992188c1d78f3ec3e2b5d597c278732eea01f1d5bde10b7db778e001213 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/model-00003-of-00004.safetensors deleted file mode 100644 index a7365908b5e13b3158faa873daf916b885a6f5fb..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fbdf43848f3d95375f617b01081f1530be32c57fbbb17f9c19a25525c4d67056 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/model-00004-of-00004.safetensors deleted file mode 100644 index 00156eb5b5a94ba198e854cd422e838f81c6496f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:df7547b496de15370109b9d1bdafd735999e8047ed08f4b47c257801d11266b9 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/special_tokens_map.json deleted file mode 100644 index cfabacc2620186cd3dd4b1dde9a37e057208636e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/special_tokens_map.json +++ /dev/null @@ -1,16 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - } -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/tokenizer.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/tokenizer_config.json deleted file mode 100644 index 5346f10a1884fed79cfa9e4a40ce7173418b5732..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1080000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/config.json deleted file mode 100644 index c8fb0b04bcf67646ee10a1ae930a7117e2e4cc5c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/model-00001-of-00004.safetensors deleted file mode 100644 index d2e23745161d808d7c130e08c2263928479c8387..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:51a69aae09dbcd577e6bc522f5e0ba0b2c5a8878867b79c1b699a8029c74cf8d -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/model-00002-of-00004.safetensors deleted file mode 100644 index 66c8c3a5bdb99f48b68a8cb3ebdbc3984da28c63..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ff09f011fa0ecfd5c4a80ac67728220ddca22577101bc5d6ffc6bdf6e7a45a64 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/model-00003-of-00004.safetensors deleted file mode 100644 index a1d5575aa0ca42aa1e348930624b9e75fa0fa5a5..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:906dc263163a9090cefdb42b737fd2270c565375cf133513c25b29be861544c1 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/model-00004-of-00004.safetensors deleted file mode 100644 index b21497ceb18b686846b92ed4391d86c4b92db97c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:734e076b9b48ff11cf783658424c82b198cb56499fa7683cf242c1e982c5ec85 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/tokenizer.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/tokenizer_config.json deleted file mode 100644 index 3026161bf4fc56964bad68d35d36b5b815a3f716..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1100000/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/config.json deleted file mode 100644 index c8fb0b04bcf67646ee10a1ae930a7117e2e4cc5c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/model-00001-of-00004.safetensors deleted file mode 100644 index 36c29b299f10dbfc2ffa2b34dde7277862d4adeb..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:851d0db3e44eadb798af909603c77564318cd491b443e6cc2b2a0ca6bde0307b -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/model-00002-of-00004.safetensors deleted file mode 100644 index 34102898ecdb8378e2b1051edc5d1163f59fb278..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5a73b9e20358b2bce818efe38b257018e35c53c6ccc2da18a2138c687336990f -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/model-00003-of-00004.safetensors deleted file mode 100644 index 67d577ce1ba69b1de76686cb395b761136f29efb..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f9939be102305deb8affe9b97ff5854a07ce0bc94d477b25d47f1e33074acc28 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/model-00004-of-00004.safetensors deleted file mode 100644 index d1165c5a180bb2097c168974f6fb73471bb505e6..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d607c90b308c517b730de2b7276fdc7f14f19767369a5f3deb100e9fa92fa4ac -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/tokenizer.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/tokenizer_config.json deleted file mode 100644 index 3026161bf4fc56964bad68d35d36b5b815a3f716..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1120000/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/config.json deleted file mode 100644 index c8fb0b04bcf67646ee10a1ae930a7117e2e4cc5c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/model-00001-of-00004.safetensors deleted file mode 100644 index 01865ecd52efd271d815b6797cf2db587556c4b5..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ec118c7baa399242bcd2d42e574b66264627c0e2da71441ed718e7cc46e78bab -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/model-00002-of-00004.safetensors deleted file mode 100644 index efb79da25589a6ad3cc505a4d2ea582a9e13eb55..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f76de8db6f4d28d58922735ddc32c2175b29d3ebd8ca7f294a7f6db266f917e3 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/model-00003-of-00004.safetensors deleted file mode 100644 index eee518c44ec155fa822cd8025acaf7c0ef6fd6b0..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:bfd2bef7a87d55202afbf278fa7c0accdf51cd952323039401fd30792be6b061 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/model-00004-of-00004.safetensors deleted file mode 100644 index 33ada10c67879843e745f6bd6d7cf761a03c960a..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:771724d75e70c5dd5afcada7fc12b80e8facfcc76ecfbebd1c466e815c7d7147 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/tokenizer.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/tokenizer_config.json deleted file mode 100644 index 3026161bf4fc56964bad68d35d36b5b815a3f716..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1140000/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/config.json deleted file mode 100644 index c8fb0b04bcf67646ee10a1ae930a7117e2e4cc5c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/model-00001-of-00004.safetensors deleted file mode 100644 index 3a744fc22415a7fc076394bd4ee34812a70b9ab2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:30057143bb49632c2b286858045595b71069676c334305e71fa5ea7def9cafc9 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/model-00002-of-00004.safetensors deleted file mode 100644 index 002b4e0dc7069e90a6bea9a0c41e14f03fd054e5..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b8ca9526675bbaef36c55942167cc53ec759216d1250ed7cf8128e3c25035018 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/model-00003-of-00004.safetensors deleted file mode 100644 index 40c28936df21362f1933944dc1985e34e20742e4..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fe1f02e9c7ad3843c08768d9a28c0a63d8d80d43a8dc302fe3a42e045eedbe95 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/model-00004-of-00004.safetensors deleted file mode 100644 index 66542ef84200b63c5ce4ffc2aa7cccbacca51d1a..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f95b0621d1eeb329b9bd510738bab62c31db17acea4e975295633263c1487674 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/tokenizer.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/tokenizer_config.json deleted file mode 100644 index 3026161bf4fc56964bad68d35d36b5b815a3f716..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1160000/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/config.json deleted file mode 100644 index c8fb0b04bcf67646ee10a1ae930a7117e2e4cc5c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/model-00001-of-00004.safetensors deleted file mode 100644 index cb63c9bcb4440dbd7c5bbb829b9aab1f4840b1e0..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4dd999ec117147a365fd7e52f4ec5e1ea903263a7afb2f9582bfa6e6f451e507 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/model-00002-of-00004.safetensors deleted file mode 100644 index e404b6683cf9cabac5153389e18c119942b28634..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2e1ad1237f5a1891e49a19afc5bb794c15b1c6739e074bd9256ae7eb56c2c5ff -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/model-00003-of-00004.safetensors deleted file mode 100644 index de125811b3e9a09858ff3950ce6a6cdb4ab16a12..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:23f9f75344775bc582f8f601ebd7cb8a2082993f3cdc32455a75317d23bae4e5 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/model-00004-of-00004.safetensors deleted file mode 100644 index a16fac1413b2698fdfd9e0340f5f1736f8b37b38..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e227ca76eb2665761f3acc1702bac11320cab229090b742121f9a868f6b7606b -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/tokenizer.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/tokenizer_config.json deleted file mode 100644 index 3026161bf4fc56964bad68d35d36b5b815a3f716..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1180000/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/config.json deleted file mode 100644 index c8fb0b04bcf67646ee10a1ae930a7117e2e4cc5c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/model-00001-of-00004.safetensors deleted file mode 100644 index 8eaee104edef5b680284606ea69ac740f218da6d..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b85c4338173ca7cd74f802f520fed856178d698eae85d630919f5790e2fe2eca -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/model-00002-of-00004.safetensors deleted file mode 100644 index 8cf914891be28ec7f67e588e93bf040528f72dc4..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5304fd1233db4aa79a3ec2068f10916cbdf429e37641dc3543aae1fe7bfa25bf -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/model-00003-of-00004.safetensors deleted file mode 100644 index c4de15820b0b1be1eab6ad374b33837703ebab7d..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4dd0c73ae934d6d12576292ade3ae35148be845f93e55f6730096dd760506e0d -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/model-00004-of-00004.safetensors deleted file mode 100644 index 4fc11651f719ea87ae3769e78ecb5de49b47d630..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:617433ac82aacf44ff0fdfe23448567d4b79dbeb43fc7c1d37cfd73cda80c79e -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/tokenizer.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/tokenizer_config.json deleted file mode 100644 index 3026161bf4fc56964bad68d35d36b5b815a3f716..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1200000/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/config.json deleted file mode 100644 index c8fb0b04bcf67646ee10a1ae930a7117e2e4cc5c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/model-00001-of-00004.safetensors deleted file mode 100644 index 3a173bf0c364ef54a73dc0e47d8c4dd9a03e0110..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:61e7041601f0eefbb66ead1a1072a40ee67e43b557a2d8939550f929a197f42b -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/model-00002-of-00004.safetensors deleted file mode 100644 index 12015675bf59f3ab52d85b1ef78f13aa088fb80a..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ec757f966d0ca9f6748270b028086ea1880133fc9be385c6dfb6619fa0857f83 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/model-00003-of-00004.safetensors deleted file mode 100644 index 4d6a90af0dbe4dbe9956b5c95b42a3c7f3c8e5d1..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e1b48ea83003cd4584567e7e050ed3bd68ef7c483a2a67627cffe1b82bd09a50 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/model-00004-of-00004.safetensors deleted file mode 100644 index 466f200f28ebaef73ff4ba90d1a3c1af90464da0..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e47a1896788feee002ea44d82c277d56fdf7e62e56de1edadbb2eabafa641120 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/tokenizer.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/tokenizer_config.json deleted file mode 100644 index 3026161bf4fc56964bad68d35d36b5b815a3f716..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1220000/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/config.json deleted file mode 100644 index 5a697cc5fc70ea77184803009c96b76d35b6862f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": null, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/model-00001-of-00004.safetensors deleted file mode 100644 index 345c48c9db28ad5211838564d6264d81ebd14ed6..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:61510e587214cfe7991cc8f7341a8011c41f7cbb9dc04e0b87441d69e86b99a5 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/model-00002-of-00004.safetensors deleted file mode 100644 index 8462ae9578e502cb969c46fc30b7527f7bbf924d..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:99a5bc614e98b5d54ec8f0ca7c9aecbbf6281557a47e4ea9cc96163a79ee9df0 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/model-00003-of-00004.safetensors deleted file mode 100644 index b8420368ae315f1804cdbc57773d7eed161f333d..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fae2b4f9afd7dfaed22695be559f38a9c7e151be928af0d763aa69be76200557 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/model-00004-of-00004.safetensors deleted file mode 100644 index 7e3e978cc2b9362184cd820071ee1c342659396b..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f525918bb982a70103952f8d75f730436574eee975b2205f25cca1fe6e08134d -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/special_tokens_map.json deleted file mode 100644 index cfabacc2620186cd3dd4b1dde9a37e057208636e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/special_tokens_map.json +++ /dev/null @@ -1,16 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - } -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/tokenizer.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/tokenizer_config.json deleted file mode 100644 index 5346f10a1884fed79cfa9e4a40ce7173418b5732..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1240000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/config.json deleted file mode 100644 index c8fb0b04bcf67646ee10a1ae930a7117e2e4cc5c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/model-00001-of-00004.safetensors deleted file mode 100644 index 54064700be7feefcc1cf055ccbc65388b19cb53d..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c5c99983af7f54607d2a78a4acf314fd3206ebc35fa2fed526579cf32d80b83c -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/model-00002-of-00004.safetensors deleted file mode 100644 index e3afca4fd5da9969e7f81709708a30f38dd1472c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6c657fd1f93b55682a1e5b806f2c9ae3cddebaecaa382b24f88327c06c186b6f -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/model-00003-of-00004.safetensors deleted file mode 100644 index 24a30b7431382af66835311dd2d2f34147e989d5..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a7278fd3afaf207c0b01dbcafbe397831dd5a695794f59d8de973be07101ee61 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/model-00004-of-00004.safetensors deleted file mode 100644 index d3853eec8f83e33f09b77054eb2f9091d3a8cdbf..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:549796acaab56f101c701a9592a3cdc1a2c5685790c90d91ebd5c7073d47f3bd -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/tokenizer.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/tokenizer_config.json deleted file mode 100644 index 3026161bf4fc56964bad68d35d36b5b815a3f716..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1260000/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/config.json deleted file mode 100644 index c8fb0b04bcf67646ee10a1ae930a7117e2e4cc5c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/model-00001-of-00004.safetensors deleted file mode 100644 index b00d514ab63b788ca936026038edb3418fb272cc..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ea1f8b2b0a781a2b7089d8debe91b65d16af75d4f1046d5e804fdb8736a04237 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/model-00002-of-00004.safetensors deleted file mode 100644 index ce50dc3a8ac80bfa3d9633792f9586f731ea7cbe..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:feeffa4cd8118eae26fcc3fc3a6b85df008c76bc8e3f91bad8eaf6bda735733d -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/model-00003-of-00004.safetensors deleted file mode 100644 index 13c702a4f968432f37693d1af45278083cadab06..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ff28d07527be1bb76a689cebf39c763b577e4c4c1c0088822a07142a7eb0be34 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/model-00004-of-00004.safetensors deleted file mode 100644 index 5787d62531241ab2de13329c8c9c82a068cfe3c3..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:64875c64cd667a82c30ebc04dd69a6b62dcdbd3dc99b498a6f1d3b767035a9a1 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/tokenizer.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/tokenizer_config.json deleted file mode 100644 index 3026161bf4fc56964bad68d35d36b5b815a3f716..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1280000/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/config.json deleted file mode 100644 index c8fb0b04bcf67646ee10a1ae930a7117e2e4cc5c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/model-00001-of-00004.safetensors deleted file mode 100644 index 8c7309f83196cf7a5ada5fe2a97ea877e1200a60..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0645f19e51e98ab9dff52668651db1cf87585953420e13ab2bcad47fedaa3650 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/model-00002-of-00004.safetensors deleted file mode 100644 index 541b48a2cbbc8829ee496ab9afc657d5278a5b1d..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c12b9cbac9000c8250595a265c9efbf2731ee86496b86e80420cbc3488f8ea14 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/model-00003-of-00004.safetensors deleted file mode 100644 index cd4c43447e0105b46a5294168e866bdd48dfff45..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8f580bb84c67cf270884bd627eea1f1b0c70f933e5062573c98860dfd5cf3176 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/model-00004-of-00004.safetensors deleted file mode 100644 index ded523f215def4baac9930d38270e18abe08f168..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e394e4035fcffd68cf969b62e23a3b61613346c2b1dd47cdd81d7fae7927c200 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/tokenizer.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/tokenizer_config.json deleted file mode 100644 index 3026161bf4fc56964bad68d35d36b5b815a3f716..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1300000/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/config.json deleted file mode 100644 index c8fb0b04bcf67646ee10a1ae930a7117e2e4cc5c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/model-00001-of-00004.safetensors deleted file mode 100644 index 64764c83a659161dd968397e519015ddf63b71cc..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5866d9993f5bdce3535c6badf3a082d4145760451246cacff835c52cca95f4fe -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/model-00002-of-00004.safetensors deleted file mode 100644 index 2cbfb85fca354c562405a4f2333cf5f5a44fd196..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4151d206a308b34c6e66926cf20440381c2ede0f826b9784ead330796f14a7f0 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/model-00003-of-00004.safetensors deleted file mode 100644 index acb0d98bab9c21e0e1f12a39a58c87f5705f8def..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f4b7e09106f2f33f4e7044977c64cb07bb1d2025e7545a770cde17b704dbaa85 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/model-00004-of-00004.safetensors deleted file mode 100644 index 02d8272c4755143fb3c1fc6ae9552026a950f2de..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1fc79eb87786d057912430336af6ef3fd9d952d32d06126ba585c25cd4100167 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/tokenizer.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/tokenizer_config.json deleted file mode 100644 index 3026161bf4fc56964bad68d35d36b5b815a3f716..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-1320000/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/config.json deleted file mode 100644 index 5a697cc5fc70ea77184803009c96b76d35b6862f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": null, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/model-00001-of-00004.safetensors deleted file mode 100644 index 7c07717f1e850259f016fd5bedc3a0b1170bbfe4..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:286b11e7e5546cfc36ada15e3b557e317c694e079d55844571c388e3f9b841d1 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/model-00002-of-00004.safetensors deleted file mode 100644 index ba25b90d8a9fdf22832a54d73b80885caa72dd14..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2f5e1a754172ecf53842b81f0e22305219dd03d76d70af4793a7c63e95a0b09c -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/model-00003-of-00004.safetensors deleted file mode 100644 index e5af0165c458c91e29102e6031cc495a020a4b59..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:30e9d9035c0c334ff40a961461013e2b0e5d3b5a241082b1c6a9b972ab5fa499 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/model-00004-of-00004.safetensors deleted file mode 100644 index 7bd8bdcc6293cdf8606ec104dbd118fe548c13ba..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:23596edbebb976fc68b77899008c6bc2bd81bf60b4ee8fbebca4ef6ddf227fdf -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/special_tokens_map.json deleted file mode 100644 index cfabacc2620186cd3dd4b1dde9a37e057208636e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/special_tokens_map.json +++ /dev/null @@ -1,16 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - } -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/tokenizer.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/tokenizer_config.json deleted file mode 100644 index 5346f10a1884fed79cfa9e4a40ce7173418b5732..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-840000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/config.json deleted file mode 100644 index 5a697cc5fc70ea77184803009c96b76d35b6862f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": null, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/model-00001-of-00004.safetensors deleted file mode 100644 index b1b6e87bd4b58f861c41cbc5f6c45e9b9792cf89..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c96d5d0d23ddf06809f80dc4de064a092da0a4b95c6f5eb3e08cce1c09030f09 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/model-00002-of-00004.safetensors deleted file mode 100644 index ccf8f6920b207844cf8cdd4f3b7410b300127fc2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4b6283694e97faf135d20466ee5a3cde52c2c1f0934bb79266076495d2f6af42 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/model-00003-of-00004.safetensors deleted file mode 100644 index 58ae8767eae60327504cb21e54c627f9dfe3ec1f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:04524b5ae6fa1c8688076c34430300a086a0bf4a5045a14e336dabdea9111e88 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/model-00004-of-00004.safetensors deleted file mode 100644 index 3d407d8cd2df5e5e8dc1db77e965723c51b45105..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:cff22150dc77701a7efdb9c6cceb0c4ba5b2facc11457cb220a67ecee601c1bd -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/special_tokens_map.json deleted file mode 100644 index cfabacc2620186cd3dd4b1dde9a37e057208636e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/special_tokens_map.json +++ /dev/null @@ -1,16 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - } -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/tokenizer.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/tokenizer_config.json deleted file mode 100644 index 5346f10a1884fed79cfa9e4a40ce7173418b5732..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-860000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/config.json deleted file mode 100644 index c8fb0b04bcf67646ee10a1ae930a7117e2e4cc5c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/model-00001-of-00004.safetensors deleted file mode 100644 index 82e0db9840c1f40e0b2047024f5121e293fb170f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5dd6ac48c602608c04217e37015a109eb7150c11c242e7d17286d3934e77a148 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/model-00002-of-00004.safetensors deleted file mode 100644 index e41e16980f20fdabe91ec1d7bc28da3cdc41019d..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8ab12f1bc39487ea6db9767f8209d4ff76476293f5e349edfa88d7ea82c29559 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/model-00003-of-00004.safetensors deleted file mode 100644 index b99301e98b4e11bc2dde89eaa0aa7af78c9f7a8e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7fdd391378adc1c4154ab1e6ccd7b282af931e68e43cbc7c0d00abfe18440283 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/model-00004-of-00004.safetensors deleted file mode 100644 index 3f21e5273c6efe0d25c8792a5d154d81ce9d0443..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8b5c8852893345246fcfacfcc053918c53b485e62b3bb00621fa0ea387e612f8 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/tokenizer.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/tokenizer_config.json deleted file mode 100644 index 3026161bf4fc56964bad68d35d36b5b815a3f716..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-880000/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/config.json deleted file mode 100644 index c8fb0b04bcf67646ee10a1ae930a7117e2e4cc5c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/model-00001-of-00004.safetensors deleted file mode 100644 index c3e23471a10403a0c7f2657ec3ea750030fc822c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4ff48314b0e359f6efa2a55bc28e4d25b293577c9f01866117552d63f40db575 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/model-00002-of-00004.safetensors deleted file mode 100644 index 5363d1d7d8208334cd81088e6bf0a5c1a2c23a2c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:055e5caf960c9c40dc020a28e9f0e5b3ae4979b120a5e839019c5992d4d3589f -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/model-00003-of-00004.safetensors deleted file mode 100644 index 80ae09db2b86c34321886e5fa0f6d5262a0e5494..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6ea765b4b43b8e3fa31f03f9cf44547d0c7b61a237136f0a36f2ecc84a995297 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/model-00004-of-00004.safetensors deleted file mode 100644 index 429d530558f6f5ebd3ce67b86798a1ae91d8ceb9..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:9e5e04cf88134ab2678091a3b18f9531b6324307a1bda7190077b937a217cc4a -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/tokenizer.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/tokenizer_config.json deleted file mode 100644 index 3026161bf4fc56964bad68d35d36b5b815a3f716..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-900000/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/config.json deleted file mode 100644 index 5a697cc5fc70ea77184803009c96b76d35b6862f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": null, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/model-00001-of-00004.safetensors deleted file mode 100644 index f988937929901b700bc19a506cfe57060b00fac7..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:615c5fd71e80dea146c06fa99bb8a192b45a81694d867d64d92256e8e06853d4 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/model-00002-of-00004.safetensors deleted file mode 100644 index af4532d4682edb64eeebd992417b9c38d8708dec..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d2748a2746ee1981dac0a0d24083cb2a92e499c8277a874d8b5567280d408106 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/model-00003-of-00004.safetensors deleted file mode 100644 index 6032f1b8e849171c36c84dcdf56c1ce5419b41b1..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:bb5c7c4f9c69106fa21d42031f2221431c68b3aa14e76bfb283481c9a0748689 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/model-00004-of-00004.safetensors deleted file mode 100644 index 936fa11a4ab521cccfd49d9443130916dc235923..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f0223302af206888164b3e4f58ae6b755792cdab9cd99e4d7affce6c8ca2a650 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/special_tokens_map.json deleted file mode 100644 index cfabacc2620186cd3dd4b1dde9a37e057208636e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/special_tokens_map.json +++ /dev/null @@ -1,16 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - } -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/tokenizer.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/tokenizer_config.json deleted file mode 100644 index 5346f10a1884fed79cfa9e4a40ce7173418b5732..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-920000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/config.json deleted file mode 100644 index 5a697cc5fc70ea77184803009c96b76d35b6862f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": null, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/model-00001-of-00004.safetensors deleted file mode 100644 index 2246b149ea2bbbda87d19f347e60daf723844eef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6783d40769b2931f8d4e8f12751015e14770245b3d7083b8cc531f745cb909e8 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/model-00002-of-00004.safetensors deleted file mode 100644 index 6ca7a9dc75ec4bb3dbdcac2ce125fa4c549a1347..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:4d8124a088bd5b52b5c3f38264e2f3952f40e820645447fdde0aa9a303c80d91 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/model-00003-of-00004.safetensors deleted file mode 100644 index dfcccb2277ae699ec6b19c8e5794b620df3304b6..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:2a3698b9e43f2ecf1ed51d14a674bbb62e67a7590015e26cab3e84efbc896a8c -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/model-00004-of-00004.safetensors deleted file mode 100644 index fdde1efda514e6c149c5da36645ab4cc5837aa84..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d52302113485c96489f0428d31c41d9b6e354a53b5c59e6176aa46b0077ae529 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/special_tokens_map.json deleted file mode 100644 index cfabacc2620186cd3dd4b1dde9a37e057208636e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/special_tokens_map.json +++ /dev/null @@ -1,16 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - } -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/tokenizer.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/tokenizer_config.json deleted file mode 100644 index 5346f10a1884fed79cfa9e4a40ce7173418b5732..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-940000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/config.json deleted file mode 100644 index 5a697cc5fc70ea77184803009c96b76d35b6862f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": null, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/model-00001-of-00004.safetensors deleted file mode 100644 index fada8f884921e3c54a4cb4c19ec78e1bd9e3fd84..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e1d6355407710152a0182b0d76dbaa9621640afd5dbf6be06b062a2796998902 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/model-00002-of-00004.safetensors deleted file mode 100644 index d769d593c3c617b471b3d55fa360239305a7f399..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b5138035b3c179f392cdcbff1b6d55a94796d567492c51d36f46e14eadf88489 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/model-00003-of-00004.safetensors deleted file mode 100644 index a2d13309b6044a7961c7ffae03f12ac472ee071e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ea89ac4d41ba08145d1d366b1c9095559201a8900c5f8fe7e4c47a90b05f75a1 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/model-00004-of-00004.safetensors deleted file mode 100644 index 361021469b146e2e8618cec5a93eb2413a3304a1..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e373668aae865911087377ec94a33be495de989f274817618225e0244f7da665 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/special_tokens_map.json deleted file mode 100644 index cfabacc2620186cd3dd4b1dde9a37e057208636e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/special_tokens_map.json +++ /dev/null @@ -1,16 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - } -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/tokenizer.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/tokenizer_config.json deleted file mode 100644 index 5346f10a1884fed79cfa9e4a40ce7173418b5732..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-960000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/config.json deleted file mode 100644 index 5a697cc5fc70ea77184803009c96b76d35b6862f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": null, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/model-00001-of-00004.safetensors deleted file mode 100644 index 98bc15711ba004c4451dd6fe565331dc4f52ddc1..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e56a6dd46de0ef2125bef8cc9294157307ff5ab2b414d28116bd95d5f7b7e165 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/model-00002-of-00004.safetensors deleted file mode 100644 index 3b7c6a98018ba6a21dd27abe320c3ae8442899ba..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e6cba2a625a492eeb3c980a19766bcf4348731c2e1658ae5a5081d086915e435 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/model-00003-of-00004.safetensors deleted file mode 100644 index eacfeeee8a2199b5ef4546f8fac05292ade26415..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:83a5c043d3364965be28f09cd0961c221d8c306438cff0f856d22352ee8e0475 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/model-00004-of-00004.safetensors deleted file mode 100644 index c86560f91a06d7cb5f9bea637385f2e8afb6c2dd..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:910a8a0770ef360ceb524927c157adb4064b09a0956ca04a04d19b4e691761cc -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/special_tokens_map.json deleted file mode 100644 index cfabacc2620186cd3dd4b1dde9a37e057208636e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/special_tokens_map.json +++ /dev/null @@ -1,16 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - } -} diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/tokenizer.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/tokenizer_config.json deleted file mode 100644 index 5346f10a1884fed79cfa9e4a40ce7173418b5732..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-adept-phoenix/hf/step-980000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/config.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/config.json deleted file mode 100644 index 5a697cc5fc70ea77184803009c96b76d35b6862f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": null, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/model-00001-of-00004.safetensors deleted file mode 100644 index a248e70dc8acfe8b24cfc3d0822696000c6d8311..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:76b9c40a956128b78bf918cffd1a7d3c53ba1d278b23b0c8a317092fd1b8e049 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/model-00002-of-00004.safetensors deleted file mode 100644 index 166696454fc22bf548d244a0d9a216e709ae4695..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c7e14e7de93d2a0b02b69137a4f9bc8f6e720fd31f7773987e28c797f5936a97 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/model-00003-of-00004.safetensors deleted file mode 100644 index 738b5dd286e02c10ad9b2a1f06e4b606b4ad680f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a6b4380b4656f0dcf20bfc2f1cda10ff5297d14561b1cc8a2adc5a8b0266f4b2 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/model-00004-of-00004.safetensors deleted file mode 100644 index 8c8f2b58d6ef9f9e62fcf7c00b3014176e5c24c7..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0394039aaed80483e662cc81c093484b90efa1d20ca683e68a3ec3e034e3bc91 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/special_tokens_map.json deleted file mode 100644 index cfabacc2620186cd3dd4b1dde9a37e057208636e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/special_tokens_map.json +++ /dev/null @@ -1,16 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - } -} diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/tokenizer.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/tokenizer_config.json deleted file mode 100644 index 5346f10a1884fed79cfa9e4a40ce7173418b5732..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-670000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/config.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/config.json deleted file mode 100644 index c8fb0b04bcf67646ee10a1ae930a7117e2e4cc5c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/model-00001-of-00004.safetensors deleted file mode 100644 index 86fb59b215be8b628db0cfd972b4a57472d16e47..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5ecbc86d32a5478c455adbcca6634819074e065bf951215f110b89fb7333c5e5 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/model-00002-of-00004.safetensors deleted file mode 100644 index 884015eac97329c3327379f1c3f1ba259d10e76c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5c05dc34eba0d3a69340cdefe663ee885a7ce2b01e0825bb189d99b54e3c19c7 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/model-00003-of-00004.safetensors deleted file mode 100644 index e0f86e3e28ccbf2975071091f30075e79b392833..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8ed9437872c2b78fbe9276610e8eb48d38a15295b5148a6ef53ff0fa7836315c -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/model-00004-of-00004.safetensors deleted file mode 100644 index 738fef6017730c5da4e0aafa931ef9e51da6c67c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6cb5305476fcd219c6321641b2f4345fe5f2768c3b3b66b0d744e5a27abffb43 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/tokenizer.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/tokenizer_config.json deleted file mode 100644 index 3026161bf4fc56964bad68d35d36b5b815a3f716..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-680000/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/config.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/config.json deleted file mode 100644 index c8fb0b04bcf67646ee10a1ae930a7117e2e4cc5c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/model-00001-of-00004.safetensors deleted file mode 100644 index 5c5f0164595953e87b57129059d9227d536cc028..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b9c11798595854fbf9be7259434d8606cfc9629248185d79116ac53cd953e2c4 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/model-00002-of-00004.safetensors deleted file mode 100644 index 5752132c3e4b9aa79c59fcce64d464ed8d4ad9dc..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e6afae9f6001dbfedd1e3267202c3740df53edac1f211dcf0af3066fad00313e -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/model-00003-of-00004.safetensors deleted file mode 100644 index a91bb968b09f2cc1b5aaf49fc4821641f95368e6..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:fb09c67b534e788689be843aba3491043e073b6b12828846e54b3e8945443071 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/model-00004-of-00004.safetensors deleted file mode 100644 index dbb3bc7eecea001e94fb819ffa594bca505676f3..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5fa9513ab4254d5118e4760d774d4b8b172cbf2ea22ffb93f4c623432d9e8ab8 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/tokenizer.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/tokenizer_config.json deleted file mode 100644 index 3026161bf4fc56964bad68d35d36b5b815a3f716..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-690000/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/config.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/config.json deleted file mode 100644 index c8fb0b04bcf67646ee10a1ae930a7117e2e4cc5c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/model-00001-of-00004.safetensors deleted file mode 100644 index 9f809ba601ce3ca29f2fc684cc38d47ec74ff523..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:eb6de418f16bd2359f996cf30ec90910b41656e62157c6fd446b8a8ea3d936eb -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/model-00002-of-00004.safetensors deleted file mode 100644 index e6d4a4cef392f76d32f7e7c249141a329c097957..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8edc4bf721bd8b8127d5baa4764ed1835d77cba71b50239206f440e189efa27f -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/model-00003-of-00004.safetensors deleted file mode 100644 index c8a3f2d99f7ec705fa397b8e8f066b45825e4d51..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:43e5ea723d6b2de703c2c0d13c5db3beb595918abba46b72588cb08e3a8c5053 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/model-00004-of-00004.safetensors deleted file mode 100644 index 2133933fa01426931666e8c07c4c8d9814b52b55..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8164493695deb406cde268aaaec0da911ec45a6621dd316d3a855568fd0bb00e -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/tokenizer.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/tokenizer_config.json deleted file mode 100644 index 3026161bf4fc56964bad68d35d36b5b815a3f716..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-700000/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/config.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/config.json deleted file mode 100644 index c8fb0b04bcf67646ee10a1ae930a7117e2e4cc5c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/model-00001-of-00004.safetensors deleted file mode 100644 index d28f2d93c66da26914ab329a0941196b65be2c18..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:998086600ffc36e9e8cdfc2fbffe2f80a5c8048f93dbb895dc8488fcf73d03f1 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/model-00002-of-00004.safetensors deleted file mode 100644 index 9076f016857a990d9763d07c266a3faad83fcd87..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:bfecf0a54fdf3d1159068f64932a51a583de2a83d7756c36f4b4ed51c62ea4c4 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/model-00003-of-00004.safetensors deleted file mode 100644 index 6cbaf4e67196eca80e108951a68200957e938f5e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7b911d2a347f54551e9919c9dd47743d2d016c60b3ccd9aa63a3aa7c98e13319 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/model-00004-of-00004.safetensors deleted file mode 100644 index ec246d24e38e4b8f7519b69311f8c098e69a3c26..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a521edfad9f486ce9fa1cddeeffbf529514b01113d432c18123d5dac7da051c2 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/tokenizer.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/tokenizer_config.json deleted file mode 100644 index 3026161bf4fc56964bad68d35d36b5b815a3f716..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-710000/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/config.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/config.json deleted file mode 100644 index 5a697cc5fc70ea77184803009c96b76d35b6862f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": null, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/model-00001-of-00004.safetensors deleted file mode 100644 index 034d759f462f84445cca8bfadf77e6db1484ac9e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c7c03834130a4c8f699ad3d5777ca583e7cd3e05bc31a8f1bc0bb6b9ead0d394 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/model-00002-of-00004.safetensors deleted file mode 100644 index 1dc0368549e988b69dba80ae11880b227f8ba554..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d1d5c714dca0625f262e3b96762ba6c9f4f92ee127e24c6cdd4ab5a44f52c44f -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/model-00003-of-00004.safetensors deleted file mode 100644 index 62a4c667711a70432abc0f218d8db2946a4b7f66..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8a7d7e627254c5391d795e7a9b54100967313f62dac01293a1e3475cebeea869 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/model-00004-of-00004.safetensors deleted file mode 100644 index 40d4571249e3687c3848d93e2b978ac3731eec43..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7bba08e96d7bac098a13337f8a4dedc12a50a2ad1b9538a552e746746d5ac93d -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/special_tokens_map.json deleted file mode 100644 index cfabacc2620186cd3dd4b1dde9a37e057208636e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/special_tokens_map.json +++ /dev/null @@ -1,16 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - } -} diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/tokenizer.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/tokenizer_config.json deleted file mode 100644 index 5346f10a1884fed79cfa9e4a40ce7173418b5732..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-720000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/config.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/config.json deleted file mode 100644 index c8fb0b04bcf67646ee10a1ae930a7117e2e4cc5c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/model-00001-of-00004.safetensors deleted file mode 100644 index b34cbcd823922218e5ba58a44cc3f1dd5adec717..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e77b189b01b30fbbfa607bf51d0d5f8608da7a66ceeb00448a5ad5c86e090bb2 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/model-00002-of-00004.safetensors deleted file mode 100644 index df8622c47fa032e63d94257972047543aac9bf01..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:262063a80afb717e851c7d214a27d425eecbc17b1efb6fd0f1086d878a031558 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/model-00003-of-00004.safetensors deleted file mode 100644 index 1accc8c499af2d66a0827bcd7ed2f54c28fb03b5..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:16e845ce3acd9810aa7d0087d010581e85e6f5ae70fa5e4ea97663404017e04c -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/model-00004-of-00004.safetensors deleted file mode 100644 index 09f2978504993769c5e830f663849e94cf298875..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:62c2c024488736ed2720d16fc8ae8f91ef47076e48828c7048c10ede8ddd6a76 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/tokenizer.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/tokenizer_config.json deleted file mode 100644 index 3026161bf4fc56964bad68d35d36b5b815a3f716..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase2/hf/step-730000/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/config.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/config.json deleted file mode 100644 index 5a697cc5fc70ea77184803009c96b76d35b6862f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": null, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/model-00001-of-00004.safetensors deleted file mode 100644 index 5eca1b883378aebba1be09250bda19913a912a3f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f9ed0e05a1b42296d7ab4f3a9b81eca1fdd1f105dcaa78c7bdb92332a2740ef9 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/model-00002-of-00004.safetensors deleted file mode 100644 index c41f1704b2d871159d6cc99cbba37b36a72c9427..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7d9c554d9bc91265293518e317afa2578a499313cbb8fdf570a467b4bc0c8d7e -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/model-00003-of-00004.safetensors deleted file mode 100644 index 34244347b09ada37224777f24149430efc3eac40..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:558123ba2a6839f700b06a4180255f597ff6db0dc0acee16b80c68bbaa3bfee0 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/model-00004-of-00004.safetensors deleted file mode 100644 index 6db4dec289ddb58dd427c17572ea8a9547acf276..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:821e89a155bc07685bac676cbf988c753c3403ff2d69ade2445bd20daa417ba4 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/special_tokens_map.json deleted file mode 100644 index cfabacc2620186cd3dd4b1dde9a37e057208636e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/special_tokens_map.json +++ /dev/null @@ -1,16 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - } -} diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/tokenizer.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/tokenizer_config.json deleted file mode 100644 index 5346f10a1884fed79cfa9e4a40ce7173418b5732..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-740000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/config.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/config.json deleted file mode 100644 index c8fb0b04bcf67646ee10a1ae930a7117e2e4cc5c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/model-00001-of-00004.safetensors deleted file mode 100644 index b1f9129e0ce4b56b35e0d45ed39abde0ffe57494..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:86b1659b0788b993a64f14050115bda7de4414743c067a76c370089305f3e9d5 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/model-00002-of-00004.safetensors deleted file mode 100644 index e11b97c74d6be0137ca314ef5655c0d32a88e8e6..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c983e29e528a7a5d2a89ee68ddc465d8859ebdfcd8ccf7d389423af6a95c85bb -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/model-00003-of-00004.safetensors deleted file mode 100644 index 2e3afa2314898a06d5e960662a53e7a3f311f698..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:33990bd6af39571fc951a2159ef735bf7fdb93e08b2217f1ea511bc92f096cc1 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/model-00004-of-00004.safetensors deleted file mode 100644 index 1df629f841152208d00d3d79a289a4745fac0352..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0ffd33de6ecaa445bfb47806659d55b1554e2bb275615fb1730c24a3bd24c762 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/tokenizer.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/tokenizer_config.json deleted file mode 100644 index 3026161bf4fc56964bad68d35d36b5b815a3f716..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-760000/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/config.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/config.json deleted file mode 100644 index c8fb0b04bcf67646ee10a1ae930a7117e2e4cc5c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/model-00001-of-00004.safetensors deleted file mode 100644 index 4b877758b9fe00979ded2c77a33e6f8e50208bab..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:ce79fa09af56ecd00fc6bbe7ba165b2b4987a5d8b9cbfa42e753fdb0bc3559a1 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/model-00002-of-00004.safetensors deleted file mode 100644 index 2df6f0be2374226c82d6ab8b224d1c635bbdd571..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d9f8e88a0eecb4c745669acf93858057b3ec59a706452e69184f81cf60a8256d -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/model-00003-of-00004.safetensors deleted file mode 100644 index 923eef7eea527cbb3035e777fc7436a770e98c9d..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:73f608ae82e2053f32874d435fccbd05f2db619161a23f34a3d82635a3a74304 -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/model-00004-of-00004.safetensors deleted file mode 100644 index 57faf1f4b4d1da08c35e62aa690563824044b708..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5078e5a5bdd2f1832a5ab4f2163774cc09a6efeb52d569e5f610999924d30228 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/tokenizer.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/tokenizer_config.json deleted file mode 100644 index 3026161bf4fc56964bad68d35d36b5b815a3f716..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-780000/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/config.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/config.json deleted file mode 100644 index 5a697cc5fc70ea77184803009c96b76d35b6862f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": null, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/model-00001-of-00004.safetensors deleted file mode 100644 index 86992e82232da1a0bf2f95a70b0e960e837d6627..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:73aa976565ef197d7e7da7964372d791854d77706d5ae7a2fa4cf018b9e7c976 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/model-00002-of-00004.safetensors deleted file mode 100644 index e26566e0dadfa377526a59f389d8958c4160dd3d..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:97cf3055457cbc0543f13d4d67e275f788ce839a2c44952ea27de095fc106e29 -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/model-00003-of-00004.safetensors deleted file mode 100644 index be06d0a1c351a788cf9366e098342064bd1fc2ab..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6a0c426c795b2b1d1bbbbffcecc956853320d2a6c53d3bd0568db2880e92836f -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/model-00004-of-00004.safetensors deleted file mode 100644 index fce99f484ce8c8e8751828d6d6f996868f75a56c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a668915925ec8024563f7034a956cfb00c6e5e33e7da2518e9f172c53ff65894 -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/special_tokens_map.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/special_tokens_map.json deleted file mode 100644 index cfabacc2620186cd3dd4b1dde9a37e057208636e..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/special_tokens_map.json +++ /dev/null @@ -1,16 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - } -} diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/tokenizer.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/tokenizer_config.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/tokenizer_config.json deleted file mode 100644 index 5346f10a1884fed79cfa9e4a40ce7173418b5732..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-800000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/config.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/config.json deleted file mode 100644 index c8fb0b04bcf67646ee10a1ae930a7117e2e4cc5c..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/model-00001-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/model-00001-of-00004.safetensors deleted file mode 100644 index e89ceaa03ced2659c6ac2343649f47ee697145ee..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1713ec7668422385db16f0b31a12cfb93670f6ee61555e548f1517f8923b9ce4 -size 9831465704 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/model-00002-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/model-00002-of-00004.safetensors deleted file mode 100644 index 4d1221de8ad3d8cf755d52e23b42ba60608de94a..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a812786892d16754f821c4fff94e30d36fb06a4c8e46938f2f129fb5d9aa758b -size 9865007800 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/model-00003-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/model-00003-of-00004.safetensors deleted file mode 100644 index a1f0951881dea82501e0bf878b58a4cd2414765d..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:56e583f31e089b0a488a7202ad945150899586a782b175934d1d00f147219c7b -size 8221912272 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/model-00004-of-00004.safetensors b/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/model-00004-of-00004.safetensors deleted file mode 100644 index dc98b8b32a5f9d6be10f9ab67ca9d4b23bda1f52..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:69af15bea9a671df7fa8b68237590049181fcc61fb7648afff0171b18c29d2cc -size 4202692840 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/model.safetensors.index.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/special_tokens_map.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/tokenizer.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/tokenizer_config.json b/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/tokenizer_config.json deleted file mode 100644 index 3026161bf4fc56964bad68d35d36b5b815a3f716..0000000000000000000000000000000000000000 --- a/checkpoints/llama-8b-tootsie-phase3/hf/step-819999/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/config.json b/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/config.json deleted file mode 100644 index 76855f76e617df4689ffa739ed356e2f8053e416..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": null, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.51.3", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/model-00001-of-00004.safetensors b/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/model-00001-of-00004.safetensors deleted file mode 100644 index c08d0915dd317b8081be5e5505b83e15d07bf514..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:7d489975e373b2511d4b19ae60a388383f43eac731797618b63db5ff1f87924a -size 9831465704 diff --git a/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/model-00002-of-00004.safetensors b/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/model-00002-of-00004.safetensors deleted file mode 100644 index 5ed530d0d4d686448750bee2a50258cf7b3ca04b..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:3974f53217c73f51de651bf00d7e28d73157b886356cf13de1fb391494acf27f -size 9865007800 diff --git a/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/model-00003-of-00004.safetensors b/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/model-00003-of-00004.safetensors deleted file mode 100644 index ffa411080fc49d755921f1cdef050de49575b7c9..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1f6ec3a7cac62c6b0229b48bdf0655b01522fbf29e478278cce1ab9b0fb94179 -size 8221912272 diff --git a/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/model-00004-of-00004.safetensors b/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/model-00004-of-00004.safetensors deleted file mode 100644 index 126cc9fd3a96cf6f773fa05a2e86701b41fad7a6..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:a910404f1e332ec92e8410e5eacd6436ed3482ec78357c4bd84415fcd2cb1238 -size 4202692840 diff --git a/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/model.safetensors.index.json b/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/special_tokens_map.json b/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/special_tokens_map.json deleted file mode 100644 index cfabacc2620186cd3dd4b1dde9a37e057208636e..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/special_tokens_map.json +++ /dev/null @@ -1,16 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - } -} diff --git a/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/tokenizer.json b/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/tokenizer_config.json b/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/tokenizer_config.json deleted file mode 100644 index 795f75993a20250b35fee4a0685d080b1a01ab2b..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-deeper-starling/hf/step-1419999/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "tokenizer_class": "PreTrainedTokenizer" -} diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/config.json b/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/config.json deleted file mode 100644 index 76855f76e617df4689ffa739ed356e2f8053e416..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": null, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.51.3", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/model-00001-of-00004.safetensors b/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/model-00001-of-00004.safetensors deleted file mode 100644 index 4347122f0b985488e09a356f019c6f40e761fe4c..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:79d18fd0d17af81a911a166326e7660b55536d88a2d73f019f6dbb61f1115212 -size 9831465704 diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/model-00002-of-00004.safetensors b/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/model-00002-of-00004.safetensors deleted file mode 100644 index 1a88af6566627ef8017f297c303c842dc45c8b62..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:d2a11b3698a7b83f6889c312298f828c15f22355048bf0ba91d1bb1f76a2384b -size 9865007800 diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/model-00003-of-00004.safetensors b/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/model-00003-of-00004.safetensors deleted file mode 100644 index 039fc4eb263e517f4af57fcb5d7c516698d3d228..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:c62fc3526bf2b9e9bf66c80149427f1b760ffffba9b02e31df51fd83e52942f1 -size 8221912272 diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/model-00004-of-00004.safetensors b/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/model-00004-of-00004.safetensors deleted file mode 100644 index f63774dbd46411c624b264ece773a1e6c6bf2245..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:45458fa719cf92c1f3582a6b6ab8a4967e881af1dfd665425a4763c96733300d -size 4202692840 diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/model.safetensors.index.json b/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/special_tokens_map.json b/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/special_tokens_map.json deleted file mode 100644 index cfabacc2620186cd3dd4b1dde9a37e057208636e..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/special_tokens_map.json +++ /dev/null @@ -1,16 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - } -} diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/tokenizer.json b/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/tokenizer_config.json b/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/tokenizer_config.json deleted file mode 100644 index 795f75993a20250b35fee4a0685d080b1a01ab2b..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1340000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "tokenizer_class": "PreTrainedTokenizer" -} diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/config.json b/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/config.json deleted file mode 100644 index 82cc328e0fd4fb5d1d0be51babd221c24ed4fbdb..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.51.3", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/model-00001-of-00004.safetensors b/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/model-00001-of-00004.safetensors deleted file mode 100644 index 851db4655003365a2a21f5796a59eb4079cc6a3e..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:63bb1ae451305a3931e0b61fb06bab5415de25695f65ab0225ec90d3186c5ff5 -size 9831465704 diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/model-00002-of-00004.safetensors b/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/model-00002-of-00004.safetensors deleted file mode 100644 index dd69aa373294ec3688ed9843c783f2e69a4f9171..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b5e6e1ec59689072ba0d426bdab5abfa2af2f4d263c78b60c9213c575f6c1b05 -size 9865007800 diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/model-00003-of-00004.safetensors b/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/model-00003-of-00004.safetensors deleted file mode 100644 index 59f0b709ce028b65fb8f81a926c0f29a6dc6ca87..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:02aabc24286133acce14fece3cf5c4665be14c4d07c918713be9c7f800d02c47 -size 8221912272 diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/model-00004-of-00004.safetensors b/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/model-00004-of-00004.safetensors deleted file mode 100644 index f3c4102d9ec5a7582801a296a66494ec9c7ec21f..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:b6507ff20b098b026cd8bffc2659428c079377812a8b6157144937f5bc69adf2 -size 4202692840 diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/model.safetensors.index.json b/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/special_tokens_map.json b/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/tokenizer.json b/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/tokenizer_config.json b/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/tokenizer_config.json deleted file mode 100644 index 81dd14db6632ad5b35b9d447732e37ac074873a5..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1360000/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizer" -} diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/config.json b/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/config.json deleted file mode 100644 index 82cc328e0fd4fb5d1d0be51babd221c24ed4fbdb..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": 128001, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.51.3", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/model-00001-of-00004.safetensors b/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/model-00001-of-00004.safetensors deleted file mode 100644 index 417697ca8ac1c7f95e68aa1a95e1139d2243f475..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:733f4180794bc003413cec43aebb24d2fdf093615cc04d7bfe0b985691f98229 -size 9831465704 diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/model-00002-of-00004.safetensors b/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/model-00002-of-00004.safetensors deleted file mode 100644 index 45a2316f370e55c2f87a11817d3563072709d554..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:0784c9f6aa70e5dca6f2c2af162a0de6d7149cb4ac4a7193571f11aaa3b6673d -size 9865007800 diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/model-00003-of-00004.safetensors b/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/model-00003-of-00004.safetensors deleted file mode 100644 index bdbf49ed85932b19286ccf8de3d9ff28c6b485a0..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f21c16aef8178eb103ddf54a894112d81fdbf29f9352a78b54c1ccef094e8145 -size 8221912272 diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/model-00004-of-00004.safetensors b/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/model-00004-of-00004.safetensors deleted file mode 100644 index e2d4339fe00c37226e3a52385b9c5123843907d4..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:1b81c3344d86d241244a8386b4b1adb9d1b2d21e1f24d89854009e10d8620504 -size 4202692840 diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/model.safetensors.index.json b/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/special_tokens_map.json b/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/special_tokens_map.json deleted file mode 100644 index 04829afa78a2d2df203ac846968db37269b01f7f..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/special_tokens_map.json +++ /dev/null @@ -1,17 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "pad_token": "<|end_of_text|>" -} diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/tokenizer.json b/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/tokenizer_config.json b/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/tokenizer_config.json deleted file mode 100644 index 81dd14db6632ad5b35b9d447732e37ac074873a5..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1380000/tokenizer_config.json +++ /dev/null @@ -1,2063 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "pad_token": "<|end_of_text|>", - "tokenizer_class": "PreTrainedTokenizer" -} diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/config.json b/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/config.json deleted file mode 100644 index 76855f76e617df4689ffa739ed356e2f8053e416..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": null, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.51.3", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/model-00001-of-00004.safetensors b/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/model-00001-of-00004.safetensors deleted file mode 100644 index dacbc7907397d57f84356ef96ba0704bff79504a..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:37fe7dbd8384a246546f755eab3b0908b3156f3a042303c1c7ef5986f79c26dd -size 9831465704 diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/model-00002-of-00004.safetensors b/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/model-00002-of-00004.safetensors deleted file mode 100644 index cfda403bef9914abd07a1df985a48b6639ac285c..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:266ade20f9126832d91cac58a23dfdb30a2769af14e89ea296c840ffdcff555d -size 9865007800 diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/model-00003-of-00004.safetensors b/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/model-00003-of-00004.safetensors deleted file mode 100644 index 73ed4bd6e41ef7d7a030dbdbb37d9a7dbdb40d62..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:19df71a6565cb55ac66a53184f5c18dc8f952570223647e8e04a52d027952f64 -size 8221912272 diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/model-00004-of-00004.safetensors b/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/model-00004-of-00004.safetensors deleted file mode 100644 index 79877109788e3f505e76028f91d03f9b6f6270df..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:06a9be8a942342e145136bbc49d2a20a172b72f1bb7de1a896284292977547f3 -size 4202692840 diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/model.safetensors.index.json b/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/special_tokens_map.json b/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/special_tokens_map.json deleted file mode 100644 index cfabacc2620186cd3dd4b1dde9a37e057208636e..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/special_tokens_map.json +++ /dev/null @@ -1,16 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - } -} diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/tokenizer.json b/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/tokenizer_config.json b/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/tokenizer_config.json deleted file mode 100644 index 795f75993a20250b35fee4a0685d080b1a01ab2b..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-sensible-starling/hf/step-1399999/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "tokenizer_class": "PreTrainedTokenizer" -} diff --git a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/config.json b/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/config.json deleted file mode 100644 index 5a697cc5fc70ea77184803009c96b76d35b6862f..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": null, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/model-00001-of-00004.safetensors b/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/model-00001-of-00004.safetensors deleted file mode 100644 index 0ec240b6c1e4c8308cc747f190405cc692f1f437..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:382428dfe7972ff84bb00db12d5460a00fb55ca996c6f83966efc833dd03680d -size 9831465704 diff --git a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/model-00002-of-00004.safetensors b/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/model-00002-of-00004.safetensors deleted file mode 100644 index eb21a483943d4b8099f8754f6549129f8b10f1ca..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:f39bda0804b38d7c49912b12ccba6ef2b172ba41572233a36ca81a12f0a0daa6 -size 9865007800 diff --git a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/model-00003-of-00004.safetensors b/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/model-00003-of-00004.safetensors deleted file mode 100644 index 4dcaa2eacff6b109aab12b3d9cd312d62e9741ec..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:8382c9374f17afec567a4470d6cfbde7cf63b00b5a624323ac9cc6f1f5d9ba0a -size 8221912272 diff --git a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/model-00004-of-00004.safetensors b/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/model-00004-of-00004.safetensors deleted file mode 100644 index 4031e994c74a7883ddc070d5e3500f8c55a2b01f..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:580354593a532025e4118d32b26fbfc735f1a991acad657b5c9a15286d5a469e -size 4202692840 diff --git a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/model.safetensors.index.json b/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/special_tokens_map.json b/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/special_tokens_map.json deleted file mode 100644 index cfabacc2620186cd3dd4b1dde9a37e057208636e..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/special_tokens_map.json +++ /dev/null @@ -1,16 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - } -} diff --git a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/tokenizer.json b/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/tokenizer_config.json b/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/tokenizer_config.json deleted file mode 100644 index 5346f10a1884fed79cfa9e4a40ce7173418b5732..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-820000/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/config.json b/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/config.json deleted file mode 100644 index 5a697cc5fc70ea77184803009c96b76d35b6862f..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/config.json +++ /dev/null @@ -1 +0,0 @@ -{"vocab_size": 128256, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 14336, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 8, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 500000, "rope_scaling": {"factor": 8.0, "low_freq_factor": 1.0, "high_freq_factor": 4.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "attention_bias": false, "attention_dropout": 0.0, "mlp_bias": false, "head_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": false, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": [128000, 128001], "architectures": ["LlamaForCausalLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 128000, "pad_token_id": null, "eos_token_id": 128001, "sep_token_id": null, "decoder_start_token_id": 128000, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "transformers_version": "4.47.0", "model_type": "llama"} \ No newline at end of file diff --git a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/model-00001-of-00004.safetensors b/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/model-00001-of-00004.safetensors deleted file mode 100644 index b16cebd95c7f890cab167ff97c0ed0bb3f8e0ce3..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/model-00001-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:5adcb6a6be783d0d2cf195189ad222179bf6386eb07ec2b8b6a1f14acd7a72a0 -size 9831465704 diff --git a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/model-00002-of-00004.safetensors b/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/model-00002-of-00004.safetensors deleted file mode 100644 index 2f7a79013ebdbba1917e54e1de5527fe58554835..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/model-00002-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:47528836ff5bd97b2de119e1f33af1b10e0ec8c0e68823c100ebe87d258b5267 -size 9865007800 diff --git a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/model-00003-of-00004.safetensors b/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/model-00003-of-00004.safetensors deleted file mode 100644 index 45688653ab4ec7d3251c7b8eb0be2b8f495d451e..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/model-00003-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:e3b54cf391c77a5bb2443787bcddd983c2820bfd2285dfd67bb3d2e1cec42958 -size 8221912272 diff --git a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/model-00004-of-00004.safetensors b/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/model-00004-of-00004.safetensors deleted file mode 100644 index 83cc7b9c1cbf759c4c4093f98a25931872330846..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/model-00004-of-00004.safetensors +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6325eb906f827827dfde5dd03e2afd4805274d14845211df2187455c86f4469d -size 4202692840 diff --git a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/model.safetensors.index.json b/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/model.safetensors.index.json deleted file mode 100644 index ec0a1f0625b6d60f9ad501cc5946a7c4d74ec1ef..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/model.safetensors.index.json +++ /dev/null @@ -1 +0,0 @@ -{"metadata": {"total_size": 32121044992}, "weight_map": {"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.norm.weight": "model-00003-of-00004.safetensors", "model.embed_tokens.weight": "model-00004-of-00004.safetensors", "lm_head.weight": "model-00004-of-00004.safetensors"}} \ No newline at end of file diff --git a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/special_tokens_map.json b/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/special_tokens_map.json deleted file mode 100644 index cfabacc2620186cd3dd4b1dde9a37e057208636e..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/special_tokens_map.json +++ /dev/null @@ -1,16 +0,0 @@ -{ - "bos_token": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - }, - "eos_token": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false - } -} diff --git a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/tokenizer.json b/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/tokenizer.json deleted file mode 100644 index 1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/tokenizer.json +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b -size 17209920 diff --git a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/tokenizer_config.json b/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/tokenizer_config.json deleted file mode 100644 index 5346f10a1884fed79cfa9e4a40ce7173418b5732..0000000000000000000000000000000000000000 --- a/checkpoints/tootsie-8b-soft-raccoon-3/hf/step-829999/tokenizer_config.json +++ /dev/null @@ -1,2062 +0,0 @@ -{ - "added_tokens_decoder": { - "128000": { - "content": "<|begin_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128001": { - "content": "<|end_of_text|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128002": { - "content": "<|reserved_special_token_0|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128003": { - "content": "<|reserved_special_token_1|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128004": { - "content": "<|finetune_right_pad_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128005": { - "content": "<|reserved_special_token_2|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128006": { - "content": "<|start_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128007": { - "content": "<|end_header_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128008": { - "content": "<|eom_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128009": { - "content": "<|eot_id|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128010": { - "content": "<|python_tag|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128011": { - "content": "<|reserved_special_token_3|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128012": { - "content": "<|reserved_special_token_4|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128013": { - "content": "<|reserved_special_token_5|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128014": { - "content": "<|reserved_special_token_6|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128015": { - "content": "<|reserved_special_token_7|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128016": { - "content": "<|reserved_special_token_8|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128017": { - "content": "<|reserved_special_token_9|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128018": { - "content": "<|reserved_special_token_10|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128019": { - "content": "<|reserved_special_token_11|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128020": { - "content": "<|reserved_special_token_12|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128021": { - "content": "<|reserved_special_token_13|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128022": { - "content": "<|reserved_special_token_14|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128023": { - "content": "<|reserved_special_token_15|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128024": { - "content": "<|reserved_special_token_16|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128025": { - "content": "<|reserved_special_token_17|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128026": { - "content": "<|reserved_special_token_18|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128027": { - "content": "<|reserved_special_token_19|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128028": { - "content": "<|reserved_special_token_20|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128029": { - "content": "<|reserved_special_token_21|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128030": { - "content": "<|reserved_special_token_22|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128031": { - "content": "<|reserved_special_token_23|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128032": { - "content": "<|reserved_special_token_24|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128033": { - "content": "<|reserved_special_token_25|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128034": { - "content": "<|reserved_special_token_26|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128035": { - "content": "<|reserved_special_token_27|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128036": { - "content": "<|reserved_special_token_28|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128037": { - "content": "<|reserved_special_token_29|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128038": { - "content": "<|reserved_special_token_30|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128039": { - "content": "<|reserved_special_token_31|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128040": { - "content": "<|reserved_special_token_32|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128041": { - "content": "<|reserved_special_token_33|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128042": { - "content": "<|reserved_special_token_34|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128043": { - "content": "<|reserved_special_token_35|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128044": { - "content": "<|reserved_special_token_36|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128045": { - "content": "<|reserved_special_token_37|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128046": { - "content": "<|reserved_special_token_38|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128047": { - "content": "<|reserved_special_token_39|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128048": { - "content": "<|reserved_special_token_40|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128049": { - "content": "<|reserved_special_token_41|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128050": { - "content": "<|reserved_special_token_42|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128051": { - "content": "<|reserved_special_token_43|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128052": { - "content": "<|reserved_special_token_44|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128053": { - "content": "<|reserved_special_token_45|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128054": { - "content": "<|reserved_special_token_46|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128055": { - "content": "<|reserved_special_token_47|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128056": { - "content": "<|reserved_special_token_48|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128057": { - "content": "<|reserved_special_token_49|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128058": { - "content": "<|reserved_special_token_50|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128059": { - "content": "<|reserved_special_token_51|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128060": { - "content": "<|reserved_special_token_52|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128061": { - "content": "<|reserved_special_token_53|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128062": { - "content": "<|reserved_special_token_54|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128063": { - "content": "<|reserved_special_token_55|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128064": { - "content": "<|reserved_special_token_56|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128065": { - "content": "<|reserved_special_token_57|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128066": { - "content": "<|reserved_special_token_58|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128067": { - "content": "<|reserved_special_token_59|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128068": { - "content": "<|reserved_special_token_60|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128069": { - "content": "<|reserved_special_token_61|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128070": { - "content": "<|reserved_special_token_62|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128071": { - "content": "<|reserved_special_token_63|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128072": { - "content": "<|reserved_special_token_64|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128073": { - "content": "<|reserved_special_token_65|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128074": { - "content": "<|reserved_special_token_66|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128075": { - "content": "<|reserved_special_token_67|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128076": { - "content": "<|reserved_special_token_68|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128077": { - "content": "<|reserved_special_token_69|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128078": { - "content": "<|reserved_special_token_70|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128079": { - "content": "<|reserved_special_token_71|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128080": { - "content": "<|reserved_special_token_72|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128081": { - "content": "<|reserved_special_token_73|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128082": { - "content": "<|reserved_special_token_74|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128083": { - "content": "<|reserved_special_token_75|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128084": { - "content": "<|reserved_special_token_76|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128085": { - "content": "<|reserved_special_token_77|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128086": { - "content": "<|reserved_special_token_78|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128087": { - "content": "<|reserved_special_token_79|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128088": { - "content": "<|reserved_special_token_80|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128089": { - "content": "<|reserved_special_token_81|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128090": { - "content": "<|reserved_special_token_82|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128091": { - "content": "<|reserved_special_token_83|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128092": { - "content": "<|reserved_special_token_84|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128093": { - "content": "<|reserved_special_token_85|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128094": { - "content": "<|reserved_special_token_86|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128095": { - "content": "<|reserved_special_token_87|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128096": { - "content": "<|reserved_special_token_88|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128097": { - "content": "<|reserved_special_token_89|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128098": { - "content": "<|reserved_special_token_90|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128099": { - "content": "<|reserved_special_token_91|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128100": { - "content": "<|reserved_special_token_92|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128101": { - "content": "<|reserved_special_token_93|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128102": { - "content": "<|reserved_special_token_94|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128103": { - "content": "<|reserved_special_token_95|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128104": { - "content": "<|reserved_special_token_96|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128105": { - "content": "<|reserved_special_token_97|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128106": { - "content": "<|reserved_special_token_98|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128107": { - "content": "<|reserved_special_token_99|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128108": { - "content": "<|reserved_special_token_100|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128109": { - "content": "<|reserved_special_token_101|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128110": { - "content": "<|reserved_special_token_102|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128111": { - "content": "<|reserved_special_token_103|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128112": { - "content": "<|reserved_special_token_104|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128113": { - "content": "<|reserved_special_token_105|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128114": { - "content": "<|reserved_special_token_106|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128115": { - "content": "<|reserved_special_token_107|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128116": { - "content": "<|reserved_special_token_108|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128117": { - "content": "<|reserved_special_token_109|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128118": { - "content": "<|reserved_special_token_110|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128119": { - "content": "<|reserved_special_token_111|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128120": { - "content": "<|reserved_special_token_112|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128121": { - "content": "<|reserved_special_token_113|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128122": { - "content": "<|reserved_special_token_114|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128123": { - "content": "<|reserved_special_token_115|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128124": { - "content": "<|reserved_special_token_116|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128125": { - "content": "<|reserved_special_token_117|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128126": { - "content": "<|reserved_special_token_118|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128127": { - "content": "<|reserved_special_token_119|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128128": { - "content": "<|reserved_special_token_120|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128129": { - "content": "<|reserved_special_token_121|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128130": { - "content": "<|reserved_special_token_122|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128131": { - "content": "<|reserved_special_token_123|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128132": { - "content": "<|reserved_special_token_124|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128133": { - "content": "<|reserved_special_token_125|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128134": { - "content": "<|reserved_special_token_126|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128135": { - "content": "<|reserved_special_token_127|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128136": { - "content": "<|reserved_special_token_128|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128137": { - "content": "<|reserved_special_token_129|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128138": { - "content": "<|reserved_special_token_130|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128139": { - "content": "<|reserved_special_token_131|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128140": { - "content": "<|reserved_special_token_132|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128141": { - "content": "<|reserved_special_token_133|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128142": { - "content": "<|reserved_special_token_134|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128143": { - "content": "<|reserved_special_token_135|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128144": { - "content": "<|reserved_special_token_136|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128145": { - "content": "<|reserved_special_token_137|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128146": { - "content": "<|reserved_special_token_138|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128147": { - "content": "<|reserved_special_token_139|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128148": { - "content": "<|reserved_special_token_140|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128149": { - "content": "<|reserved_special_token_141|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128150": { - "content": "<|reserved_special_token_142|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128151": { - "content": "<|reserved_special_token_143|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128152": { - "content": "<|reserved_special_token_144|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128153": { - "content": "<|reserved_special_token_145|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128154": { - "content": "<|reserved_special_token_146|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128155": { - "content": "<|reserved_special_token_147|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128156": { - "content": "<|reserved_special_token_148|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128157": { - "content": "<|reserved_special_token_149|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128158": { - "content": "<|reserved_special_token_150|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128159": { - "content": "<|reserved_special_token_151|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128160": { - "content": "<|reserved_special_token_152|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128161": { - "content": "<|reserved_special_token_153|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128162": { - "content": "<|reserved_special_token_154|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128163": { - "content": "<|reserved_special_token_155|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128164": { - "content": "<|reserved_special_token_156|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128165": { - "content": "<|reserved_special_token_157|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128166": { - "content": "<|reserved_special_token_158|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128167": { - "content": "<|reserved_special_token_159|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128168": { - "content": "<|reserved_special_token_160|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128169": { - "content": "<|reserved_special_token_161|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128170": { - "content": "<|reserved_special_token_162|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128171": { - "content": "<|reserved_special_token_163|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128172": { - "content": "<|reserved_special_token_164|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128173": { - "content": "<|reserved_special_token_165|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128174": { - "content": "<|reserved_special_token_166|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128175": { - "content": "<|reserved_special_token_167|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128176": { - "content": "<|reserved_special_token_168|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128177": { - "content": "<|reserved_special_token_169|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128178": { - "content": "<|reserved_special_token_170|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128179": { - "content": "<|reserved_special_token_171|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128180": { - "content": "<|reserved_special_token_172|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128181": { - "content": "<|reserved_special_token_173|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128182": { - "content": "<|reserved_special_token_174|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128183": { - "content": "<|reserved_special_token_175|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128184": { - "content": "<|reserved_special_token_176|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128185": { - "content": "<|reserved_special_token_177|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128186": { - "content": "<|reserved_special_token_178|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128187": { - "content": "<|reserved_special_token_179|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128188": { - "content": "<|reserved_special_token_180|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128189": { - "content": "<|reserved_special_token_181|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128190": { - "content": "<|reserved_special_token_182|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128191": { - "content": "<|reserved_special_token_183|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128192": { - "content": "<|reserved_special_token_184|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128193": { - "content": "<|reserved_special_token_185|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128194": { - "content": "<|reserved_special_token_186|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128195": { - "content": "<|reserved_special_token_187|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128196": { - "content": "<|reserved_special_token_188|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128197": { - "content": "<|reserved_special_token_189|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128198": { - "content": "<|reserved_special_token_190|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128199": { - "content": "<|reserved_special_token_191|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128200": { - "content": "<|reserved_special_token_192|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128201": { - "content": "<|reserved_special_token_193|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128202": { - "content": "<|reserved_special_token_194|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128203": { - "content": "<|reserved_special_token_195|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128204": { - "content": "<|reserved_special_token_196|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128205": { - "content": "<|reserved_special_token_197|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128206": { - "content": "<|reserved_special_token_198|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128207": { - "content": "<|reserved_special_token_199|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128208": { - "content": "<|reserved_special_token_200|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128209": { - "content": "<|reserved_special_token_201|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128210": { - "content": "<|reserved_special_token_202|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128211": { - "content": "<|reserved_special_token_203|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128212": { - "content": "<|reserved_special_token_204|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128213": { - "content": "<|reserved_special_token_205|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128214": { - "content": "<|reserved_special_token_206|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128215": { - "content": "<|reserved_special_token_207|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128216": { - "content": "<|reserved_special_token_208|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128217": { - "content": "<|reserved_special_token_209|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128218": { - "content": "<|reserved_special_token_210|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128219": { - "content": "<|reserved_special_token_211|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128220": { - "content": "<|reserved_special_token_212|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128221": { - "content": "<|reserved_special_token_213|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128222": { - "content": "<|reserved_special_token_214|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128223": { - "content": "<|reserved_special_token_215|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128224": { - "content": "<|reserved_special_token_216|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128225": { - "content": "<|reserved_special_token_217|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128226": { - "content": "<|reserved_special_token_218|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128227": { - "content": "<|reserved_special_token_219|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128228": { - "content": "<|reserved_special_token_220|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128229": { - "content": "<|reserved_special_token_221|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128230": { - "content": "<|reserved_special_token_222|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128231": { - "content": "<|reserved_special_token_223|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128232": { - "content": "<|reserved_special_token_224|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128233": { - "content": "<|reserved_special_token_225|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128234": { - "content": "<|reserved_special_token_226|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128235": { - "content": "<|reserved_special_token_227|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128236": { - "content": "<|reserved_special_token_228|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128237": { - "content": "<|reserved_special_token_229|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128238": { - "content": "<|reserved_special_token_230|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128239": { - "content": "<|reserved_special_token_231|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128240": { - "content": "<|reserved_special_token_232|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128241": { - "content": "<|reserved_special_token_233|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128242": { - "content": "<|reserved_special_token_234|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128243": { - "content": "<|reserved_special_token_235|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128244": { - "content": "<|reserved_special_token_236|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128245": { - "content": "<|reserved_special_token_237|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128246": { - "content": "<|reserved_special_token_238|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128247": { - "content": "<|reserved_special_token_239|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128248": { - "content": "<|reserved_special_token_240|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128249": { - "content": "<|reserved_special_token_241|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128250": { - "content": "<|reserved_special_token_242|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128251": { - "content": "<|reserved_special_token_243|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128252": { - "content": "<|reserved_special_token_244|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128253": { - "content": "<|reserved_special_token_245|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128254": { - "content": "<|reserved_special_token_246|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - }, - "128255": { - "content": "<|reserved_special_token_247|>", - "lstrip": false, - "normalized": false, - "rstrip": false, - "single_word": false, - "special": true - } - }, - "bos_token": "<|begin_of_text|>", - "clean_up_tokenization_spaces": true, - "eos_token": "<|end_of_text|>", - "extra_special_tokens": {}, - "model_input_names": [ - "input_ids", - "attention_mask" - ], - "model_max_length": 131072, - "tokenizer_class": "PreTrainedTokenizerFast" -} diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-100000/config.json b/config.json similarity index 100% rename from checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-100000/config.json rename to config.json diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-20000/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors similarity index 100% rename from checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-20000/model-00001-of-00004.safetensors rename to model-00001-of-00004.safetensors diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-20000/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors similarity index 100% rename from checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-20000/model-00002-of-00004.safetensors rename to model-00002-of-00004.safetensors diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-20000/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors similarity index 100% rename from checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-20000/model-00003-of-00004.safetensors rename to model-00003-of-00004.safetensors diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-20000/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors similarity index 100% rename from checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-20000/model-00004-of-00004.safetensors rename to model-00004-of-00004.safetensors diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-100000/model.safetensors.index.json b/model.safetensors.index.json similarity index 100% rename from checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-100000/model.safetensors.index.json rename to model.safetensors.index.json diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-100000/special_tokens_map.json b/special_tokens_map.json similarity index 100% rename from checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-100000/special_tokens_map.json rename to special_tokens_map.json diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-100000/tokenizer.json b/tokenizer.json similarity index 100% rename from checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-100000/tokenizer.json rename to tokenizer.json diff --git a/checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-100000/tokenizer_config.json b/tokenizer_config.json similarity index 100% rename from checkpoints/llama-8b-tootsie-0.001-19ad63/hf/step-100000/tokenizer_config.json rename to tokenizer_config.json