| { | |
| "architectures": [ | |
| "Qwen3OmniMoeForConditionalGeneration" | |
| ], | |
| "assistant_token_id": 77091, | |
| "dtype": "bfloat16", | |
| "enable_audio_output": false, | |
| "im_end_token_id": 151645, | |
| "im_start_token_id": 151644, | |
| "model_type": "qwen3_omni_moe", | |
| "system_token_id": 8948, | |
| "thinker_config": { | |
| "audio_config": { | |
| "_name_or_path": "", | |
| "activation_dropout": 0, | |
| "activation_function": "gelu", | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "attention_dropout": 0, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "conv_chunksize": 500, | |
| "cross_attention_hidden_size": null, | |
| "d_model": 1280, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "downsample_hidden_size":480, | |
| "dropout": 0, | |
| "dtype": null, | |
| "early_stopping": false, | |
| "encoder_attention_heads": 20, | |
| "encoder_ffn_dim": 5120, | |
| "encoder_layers": 32, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_source_positions": 1500, | |
| "min_length": 0, | |
| "model_type": "qwen3_omni_moe_audio_encoder", | |
| "n_window": 50, | |
| "n_window_infer": 800, | |
| "no_repeat_ngram_size": 0, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 32, | |
| "num_mel_bins": 128, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_dim": 2048, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "scale_embedding": false, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false | |
| }, | |
| "audio_end_token_id": 151670, | |
| "audio_start_token_id": 151669, | |
| "audio_token_id": 151675, | |
| "dtype": "bfloat16", | |
| "image_token_id": 151655, | |
| "initializer_range": 0.02, | |
| "model_type": "qwen3_omni_moe_thinker", | |
| "position_id_per_seconds": 13, | |
| "seconds_per_chunk": 2, | |
| "text_config": { | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_sparse_step": 1, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": true, | |
| "dtype": null, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 768, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 65536, | |
| "min_length": 0, | |
| "mlp_only_layers": [], | |
| "model_type": "qwen3_omni_moe_text", | |
| "moe_intermediate_size": 768, | |
| "no_repeat_ngram_size": 0, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 32, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_experts": 128, | |
| "num_experts_per_tok": 8, | |
| "num_hidden_layers": 48, | |
| "num_key_value_heads": 4, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_router_logits": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "interleaved": true, | |
| "mrope_interleaved": true, | |
| "mrope_section": [ | |
| 24, | |
| 20, | |
| 20 | |
| ], | |
| "rope_type": "default", | |
| "type": "default" | |
| }, | |
| "rope_theta": 1000000, | |
| "router_aux_loss_coef": 0.001, | |
| "sep_token_id": null, | |
| "shared_expert_intermediate_size": 0, | |
| "sliding_window": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "use_cache": true, | |
| "use_qk_norm": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 152064 | |
| }, | |
| "user_token_id": 872, | |
| "video_token_id": 151656, | |
| "vision_config": { | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "apply_vit_abs_pos_embed": true, | |
| "architectures": null, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "deepstack_visual_indexes": [ | |
| 8, | |
| 16, | |
| 24 | |
| ], | |
| "depth": 27, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "dtype": null, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "image_size": 768, | |
| "in_channels": 3, | |
| "in_chans": 3, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4304, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "model_type": "qwen3_omni_moe_vision_encoder", | |
| "no_repeat_ngram_size": 0, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_heads": 16, | |
| "num_return_sequences": 1, | |
| "out_hidden_size": 2048, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "patch_size": 16, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "sep_token_id": null, | |
| "spatial_merge_size": 2, | |
| "spatial_patch_size": 16, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "temporal_patch_size": 2, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "tokens_per_second": 2, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false | |
| }, | |
| "vision_end_token_id": 151653, | |
| "vision_start_token_id": 151652 | |
| }, | |
| "quantization_config": { | |
| "config_groups": { | |
| "group_0": { | |
| "format": "pack-quantized", | |
| "input_activations": null, | |
| "output_activations": null, | |
| "targets": [ | |
| "Linear" | |
| ], | |
| "weights": { | |
| "actorder": null, | |
| "block_structure": null, | |
| "dynamic": false, | |
| "group_size": 32, | |
| "num_bits": 4, | |
| "observer": "mse", | |
| "observer_kwargs": {}, | |
| "strategy": "group", | |
| "symmetric": true, | |
| "type": "int" | |
| } | |
| } | |
| }, | |
| "format": "pack-quantized", | |
| "global_compression_ratio": null, | |
| "ignore": [ | |
| "thinker.audio_tower.layers.0.self_attn.k_proj", | |
| "thinker.audio_tower.layers.0.self_attn.v_proj", | |
| "thinker.audio_tower.layers.0.self_attn.q_proj", | |
| "thinker.audio_tower.layers.0.self_attn.out_proj", | |
| "thinker.audio_tower.layers.0.fc1", | |
| "thinker.audio_tower.layers.0.fc2", | |
| "thinker.audio_tower.layers.1.self_attn.k_proj", | |
| "thinker.audio_tower.layers.1.self_attn.v_proj", | |
| "thinker.audio_tower.layers.1.self_attn.q_proj", | |
| "thinker.audio_tower.layers.1.self_attn.out_proj", | |
| "thinker.audio_tower.layers.1.fc1", | |
| "thinker.audio_tower.layers.1.fc2", | |
| "thinker.audio_tower.layers.2.self_attn.k_proj", | |
| "thinker.audio_tower.layers.2.self_attn.v_proj", | |
| "thinker.audio_tower.layers.2.self_attn.q_proj", | |
| "thinker.audio_tower.layers.2.self_attn.out_proj", | |
| "thinker.audio_tower.layers.2.fc1", | |
| "thinker.audio_tower.layers.2.fc2", | |
| "thinker.audio_tower.layers.3.self_attn.k_proj", | |
| "thinker.audio_tower.layers.3.self_attn.v_proj", | |
| "thinker.audio_tower.layers.3.self_attn.q_proj", | |
| "thinker.audio_tower.layers.3.self_attn.out_proj", | |
| "thinker.audio_tower.layers.3.fc1", | |
| "thinker.audio_tower.layers.3.fc2", | |
| "thinker.audio_tower.layers.4.self_attn.k_proj", | |
| "thinker.audio_tower.layers.4.self_attn.v_proj", | |
| "thinker.audio_tower.layers.4.self_attn.q_proj", | |
| "thinker.audio_tower.layers.4.self_attn.out_proj", | |
| "thinker.audio_tower.layers.4.fc1", | |
| "thinker.audio_tower.layers.4.fc2", | |
| "thinker.audio_tower.layers.5.self_attn.k_proj", | |
| "thinker.audio_tower.layers.5.self_attn.v_proj", | |
| "thinker.audio_tower.layers.5.self_attn.q_proj", | |
| "thinker.audio_tower.layers.5.self_attn.out_proj", | |
| "thinker.audio_tower.layers.5.fc1", | |
| "thinker.audio_tower.layers.5.fc2", | |
| "thinker.audio_tower.layers.6.self_attn.k_proj", | |
| "thinker.audio_tower.layers.6.self_attn.v_proj", | |
| "thinker.audio_tower.layers.6.self_attn.q_proj", | |
| "thinker.audio_tower.layers.6.self_attn.out_proj", | |
| "thinker.audio_tower.layers.6.fc1", | |
| "thinker.audio_tower.layers.6.fc2", | |
| "thinker.audio_tower.layers.7.self_attn.k_proj", | |
| "thinker.audio_tower.layers.7.self_attn.v_proj", | |
| "thinker.audio_tower.layers.7.self_attn.q_proj", | |
| "thinker.audio_tower.layers.7.self_attn.out_proj", | |
| "thinker.audio_tower.layers.7.fc1", | |
| "thinker.audio_tower.layers.7.fc2", | |
| "thinker.audio_tower.layers.8.self_attn.k_proj", | |
| "thinker.audio_tower.layers.8.self_attn.v_proj", | |
| "thinker.audio_tower.layers.8.self_attn.q_proj", | |
| "thinker.audio_tower.layers.8.self_attn.out_proj", | |
| "thinker.audio_tower.layers.8.fc1", | |
| "thinker.audio_tower.layers.8.fc2", | |
| "thinker.audio_tower.layers.9.self_attn.k_proj", | |
| "thinker.audio_tower.layers.9.self_attn.v_proj", | |
| "thinker.audio_tower.layers.9.self_attn.q_proj", | |
| "thinker.audio_tower.layers.9.self_attn.out_proj", | |
| "thinker.audio_tower.layers.9.fc1", | |
| "thinker.audio_tower.layers.9.fc2", | |
| "thinker.audio_tower.layers.10.self_attn.k_proj", | |
| "thinker.audio_tower.layers.10.self_attn.v_proj", | |
| "thinker.audio_tower.layers.10.self_attn.q_proj", | |
| "thinker.audio_tower.layers.10.self_attn.out_proj", | |
| "thinker.audio_tower.layers.10.fc1", | |
| "thinker.audio_tower.layers.10.fc2", | |
| "thinker.audio_tower.layers.11.self_attn.k_proj", | |
| "thinker.audio_tower.layers.11.self_attn.v_proj", | |
| "thinker.audio_tower.layers.11.self_attn.q_proj", | |
| "thinker.audio_tower.layers.11.self_attn.out_proj", | |
| "thinker.audio_tower.layers.11.fc1", | |
| "thinker.audio_tower.layers.11.fc2", | |
| "thinker.audio_tower.layers.12.self_attn.k_proj", | |
| "thinker.audio_tower.layers.12.self_attn.v_proj", | |
| "thinker.audio_tower.layers.12.self_attn.q_proj", | |
| "thinker.audio_tower.layers.12.self_attn.out_proj", | |
| "thinker.audio_tower.layers.12.fc1", | |
| "thinker.audio_tower.layers.12.fc2", | |
| "thinker.audio_tower.layers.13.self_attn.k_proj", | |
| "thinker.audio_tower.layers.13.self_attn.v_proj", | |
| "thinker.audio_tower.layers.13.self_attn.q_proj", | |
| "thinker.audio_tower.layers.13.self_attn.out_proj", | |
| "thinker.audio_tower.layers.13.fc1", | |
| "thinker.audio_tower.layers.13.fc2", | |
| "thinker.audio_tower.layers.14.self_attn.k_proj", | |
| "thinker.audio_tower.layers.14.self_attn.v_proj", | |
| "thinker.audio_tower.layers.14.self_attn.q_proj", | |
| "thinker.audio_tower.layers.14.self_attn.out_proj", | |
| "thinker.audio_tower.layers.14.fc1", | |
| "thinker.audio_tower.layers.14.fc2", | |
| "thinker.audio_tower.layers.15.self_attn.k_proj", | |
| "thinker.audio_tower.layers.15.self_attn.v_proj", | |
| "thinker.audio_tower.layers.15.self_attn.q_proj", | |
| "thinker.audio_tower.layers.15.self_attn.out_proj", | |
| "thinker.audio_tower.layers.15.fc1", | |
| "thinker.audio_tower.layers.15.fc2", | |
| "thinker.audio_tower.layers.16.self_attn.k_proj", | |
| "thinker.audio_tower.layers.16.self_attn.v_proj", | |
| "thinker.audio_tower.layers.16.self_attn.q_proj", | |
| "thinker.audio_tower.layers.16.self_attn.out_proj", | |
| "thinker.audio_tower.layers.16.fc1", | |
| "thinker.audio_tower.layers.16.fc2", | |
| "thinker.audio_tower.layers.17.self_attn.k_proj", | |
| "thinker.audio_tower.layers.17.self_attn.v_proj", | |
| "thinker.audio_tower.layers.17.self_attn.q_proj", | |
| "thinker.audio_tower.layers.17.self_attn.out_proj", | |
| "thinker.audio_tower.layers.17.fc1", | |
| "thinker.audio_tower.layers.17.fc2", | |
| "thinker.audio_tower.layers.18.self_attn.k_proj", | |
| "thinker.audio_tower.layers.18.self_attn.v_proj", | |
| "thinker.audio_tower.layers.18.self_attn.q_proj", | |
| "thinker.audio_tower.layers.18.self_attn.out_proj", | |
| "thinker.audio_tower.layers.18.fc1", | |
| "thinker.audio_tower.layers.18.fc2", | |
| "thinker.audio_tower.layers.19.self_attn.k_proj", | |
| "thinker.audio_tower.layers.19.self_attn.v_proj", | |
| "thinker.audio_tower.layers.19.self_attn.q_proj", | |
| "thinker.audio_tower.layers.19.self_attn.out_proj", | |
| "thinker.audio_tower.layers.19.fc1", | |
| "thinker.audio_tower.layers.19.fc2", | |
| "thinker.audio_tower.layers.20.self_attn.k_proj", | |
| "thinker.audio_tower.layers.20.self_attn.v_proj", | |
| "thinker.audio_tower.layers.20.self_attn.q_proj", | |
| "thinker.audio_tower.layers.20.self_attn.out_proj", | |
| "thinker.audio_tower.layers.20.fc1", | |
| "thinker.audio_tower.layers.20.fc2", | |
| "thinker.audio_tower.layers.21.self_attn.k_proj", | |
| "thinker.audio_tower.layers.21.self_attn.v_proj", | |
| "thinker.audio_tower.layers.21.self_attn.q_proj", | |
| "thinker.audio_tower.layers.21.self_attn.out_proj", | |
| "thinker.audio_tower.layers.21.fc1", | |
| "thinker.audio_tower.layers.21.fc2", | |
| "thinker.audio_tower.layers.22.self_attn.k_proj", | |
| "thinker.audio_tower.layers.22.self_attn.v_proj", | |
| "thinker.audio_tower.layers.22.self_attn.q_proj", | |
| "thinker.audio_tower.layers.22.self_attn.out_proj", | |
| "thinker.audio_tower.layers.22.fc1", | |
| "thinker.audio_tower.layers.22.fc2", | |
| "thinker.audio_tower.layers.23.self_attn.k_proj", | |
| "thinker.audio_tower.layers.23.self_attn.v_proj", | |
| "thinker.audio_tower.layers.23.self_attn.q_proj", | |
| "thinker.audio_tower.layers.23.self_attn.out_proj", | |
| "thinker.audio_tower.layers.23.fc1", | |
| "thinker.audio_tower.layers.23.fc2", | |
| "thinker.audio_tower.layers.24.self_attn.k_proj", | |
| "thinker.audio_tower.layers.24.self_attn.v_proj", | |
| "thinker.audio_tower.layers.24.self_attn.q_proj", | |
| "thinker.audio_tower.layers.24.self_attn.out_proj", | |
| "thinker.audio_tower.layers.24.fc1", | |
| "thinker.audio_tower.layers.24.fc2", | |
| "thinker.audio_tower.layers.25.self_attn.k_proj", | |
| "thinker.audio_tower.layers.25.self_attn.v_proj", | |
| "thinker.audio_tower.layers.25.self_attn.q_proj", | |
| "thinker.audio_tower.layers.25.self_attn.out_proj", | |
| "thinker.audio_tower.layers.25.fc1", | |
| "thinker.audio_tower.layers.25.fc2", | |
| "thinker.audio_tower.layers.26.self_attn.k_proj", | |
| "thinker.audio_tower.layers.26.self_attn.v_proj", | |
| "thinker.audio_tower.layers.26.self_attn.q_proj", | |
| "thinker.audio_tower.layers.26.self_attn.out_proj", | |
| "thinker.audio_tower.layers.26.fc1", | |
| "thinker.audio_tower.layers.26.fc2", | |
| "thinker.audio_tower.layers.27.self_attn.k_proj", | |
| "thinker.audio_tower.layers.27.self_attn.v_proj", | |
| "thinker.audio_tower.layers.27.self_attn.q_proj", | |
| "thinker.audio_tower.layers.27.self_attn.out_proj", | |
| "thinker.audio_tower.layers.27.fc1", | |
| "thinker.audio_tower.layers.27.fc2", | |
| "thinker.audio_tower.layers.28.self_attn.k_proj", | |
| "thinker.audio_tower.layers.28.self_attn.v_proj", | |
| "thinker.audio_tower.layers.28.self_attn.q_proj", | |
| "thinker.audio_tower.layers.28.self_attn.out_proj", | |
| "thinker.audio_tower.layers.28.fc1", | |
| "thinker.audio_tower.layers.28.fc2", | |
| "thinker.audio_tower.layers.29.self_attn.k_proj", | |
| "thinker.audio_tower.layers.29.self_attn.v_proj", | |
| "thinker.audio_tower.layers.29.self_attn.q_proj", | |
| "thinker.audio_tower.layers.29.self_attn.out_proj", | |
| "thinker.audio_tower.layers.29.fc1", | |
| "thinker.audio_tower.layers.29.fc2", | |
| "thinker.audio_tower.layers.30.self_attn.k_proj", | |
| "thinker.audio_tower.layers.30.self_attn.v_proj", | |
| "thinker.audio_tower.layers.30.self_attn.q_proj", | |
| "thinker.audio_tower.layers.30.self_attn.out_proj", | |
| "thinker.audio_tower.layers.30.fc1", | |
| "thinker.audio_tower.layers.30.fc2", | |
| "thinker.audio_tower.layers.31.self_attn.k_proj", | |
| "thinker.audio_tower.layers.31.self_attn.v_proj", | |
| "thinker.audio_tower.layers.31.self_attn.q_proj", | |
| "thinker.audio_tower.layers.31.self_attn.out_proj", | |
| "thinker.audio_tower.layers.31.fc1", | |
| "thinker.audio_tower.layers.31.fc2", | |
| "thinker.audio_tower.conv_out", | |
| "thinker.audio_tower.proj1", | |
| "thinker.audio_tower.proj2", | |
| "thinker.visual.merger_list.0.mlp.0", | |
| "thinker.visual.merger_list.0.mlp.2", | |
| "thinker.visual.merger_list.1.mlp.0", | |
| "thinker.visual.merger_list.1.mlp.2", | |
| "thinker.visual.merger_list.2.mlp.0", | |
| "thinker.visual.merger_list.2.mlp.2", | |
| "thinker.visual.blocks.0.attn.qkv", | |
| "thinker.visual.blocks.0.attn.proj", | |
| "thinker.visual.blocks.0.mlp.linear_fc1", | |
| "thinker.visual.blocks.0.mlp.linear_fc2", | |
| "thinker.visual.blocks.1.attn.qkv", | |
| "thinker.visual.blocks.1.attn.proj", | |
| "thinker.visual.blocks.1.mlp.linear_fc1", | |
| "thinker.visual.blocks.1.mlp.linear_fc2", | |
| "thinker.visual.blocks.2.attn.qkv", | |
| "thinker.visual.blocks.2.attn.proj", | |
| "thinker.visual.blocks.2.mlp.linear_fc1", | |
| "thinker.visual.blocks.2.mlp.linear_fc2", | |
| "thinker.visual.blocks.3.attn.qkv", | |
| "thinker.visual.blocks.3.attn.proj", | |
| "thinker.visual.blocks.3.mlp.linear_fc1", | |
| "thinker.visual.blocks.3.mlp.linear_fc2", | |
| "thinker.visual.blocks.4.attn.qkv", | |
| "thinker.visual.blocks.4.attn.proj", | |
| "thinker.visual.blocks.4.mlp.linear_fc1", | |
| "thinker.visual.blocks.4.mlp.linear_fc2", | |
| "thinker.visual.blocks.5.attn.qkv", | |
| "thinker.visual.blocks.5.attn.proj", | |
| "thinker.visual.blocks.5.mlp.linear_fc1", | |
| "thinker.visual.blocks.5.mlp.linear_fc2", | |
| "thinker.visual.blocks.6.attn.qkv", | |
| "thinker.visual.blocks.6.attn.proj", | |
| "thinker.visual.blocks.6.mlp.linear_fc1", | |
| "thinker.visual.blocks.6.mlp.linear_fc2", | |
| "thinker.visual.blocks.7.attn.qkv", | |
| "thinker.visual.blocks.7.attn.proj", | |
| "thinker.visual.blocks.7.mlp.linear_fc1", | |
| "thinker.visual.blocks.7.mlp.linear_fc2", | |
| "thinker.visual.blocks.8.attn.qkv", | |
| "thinker.visual.blocks.8.attn.proj", | |
| "thinker.visual.blocks.8.mlp.linear_fc1", | |
| "thinker.visual.blocks.8.mlp.linear_fc2", | |
| "thinker.visual.blocks.9.attn.qkv", | |
| "thinker.visual.blocks.9.attn.proj", | |
| "thinker.visual.blocks.9.mlp.linear_fc1", | |
| "thinker.visual.blocks.9.mlp.linear_fc2", | |
| "thinker.visual.blocks.10.attn.qkv", | |
| "thinker.visual.blocks.10.attn.proj", | |
| "thinker.visual.blocks.10.mlp.linear_fc1", | |
| "thinker.visual.blocks.10.mlp.linear_fc2", | |
| "thinker.visual.blocks.11.attn.qkv", | |
| "thinker.visual.blocks.11.attn.proj", | |
| "thinker.visual.blocks.11.mlp.linear_fc1", | |
| "thinker.visual.blocks.11.mlp.linear_fc2", | |
| "thinker.visual.blocks.12.attn.qkv", | |
| "thinker.visual.blocks.12.attn.proj", | |
| "thinker.visual.blocks.12.mlp.linear_fc1", | |
| "thinker.visual.blocks.12.mlp.linear_fc2", | |
| "thinker.visual.blocks.13.attn.qkv", | |
| "thinker.visual.blocks.13.attn.proj", | |
| "thinker.visual.blocks.13.mlp.linear_fc1", | |
| "thinker.visual.blocks.13.mlp.linear_fc2", | |
| "thinker.visual.blocks.14.attn.qkv", | |
| "thinker.visual.blocks.14.attn.proj", | |
| "thinker.visual.blocks.14.mlp.linear_fc1", | |
| "thinker.visual.blocks.14.mlp.linear_fc2", | |
| "thinker.visual.blocks.15.attn.qkv", | |
| "thinker.visual.blocks.15.attn.proj", | |
| "thinker.visual.blocks.15.mlp.linear_fc1", | |
| "thinker.visual.blocks.15.mlp.linear_fc2", | |
| "thinker.visual.blocks.16.attn.qkv", | |
| "thinker.visual.blocks.16.attn.proj", | |
| "thinker.visual.blocks.16.mlp.linear_fc1", | |
| "thinker.visual.blocks.16.mlp.linear_fc2", | |
| "thinker.visual.blocks.17.attn.qkv", | |
| "thinker.visual.blocks.17.attn.proj", | |
| "thinker.visual.blocks.17.mlp.linear_fc1", | |
| "thinker.visual.blocks.17.mlp.linear_fc2", | |
| "thinker.visual.blocks.18.attn.qkv", | |
| "thinker.visual.blocks.18.attn.proj", | |
| "thinker.visual.blocks.18.mlp.linear_fc1", | |
| "thinker.visual.blocks.18.mlp.linear_fc2", | |
| "thinker.visual.blocks.19.attn.qkv", | |
| "thinker.visual.blocks.19.attn.proj", | |
| "thinker.visual.blocks.19.mlp.linear_fc1", | |
| "thinker.visual.blocks.19.mlp.linear_fc2", | |
| "thinker.visual.blocks.20.attn.qkv", | |
| "thinker.visual.blocks.20.attn.proj", | |
| "thinker.visual.blocks.20.mlp.linear_fc1", | |
| "thinker.visual.blocks.20.mlp.linear_fc2", | |
| "thinker.visual.blocks.21.attn.qkv", | |
| "thinker.visual.blocks.21.attn.proj", | |
| "thinker.visual.blocks.21.mlp.linear_fc1", | |
| "thinker.visual.blocks.21.mlp.linear_fc2", | |
| "thinker.visual.blocks.22.attn.qkv", | |
| "thinker.visual.blocks.22.attn.proj", | |
| "thinker.visual.blocks.22.mlp.linear_fc1", | |
| "thinker.visual.blocks.22.mlp.linear_fc2", | |
| "thinker.visual.blocks.23.attn.qkv", | |
| "thinker.visual.blocks.23.attn.proj", | |
| "thinker.visual.blocks.23.mlp.linear_fc1", | |
| "thinker.visual.blocks.23.mlp.linear_fc2", | |
| "thinker.visual.blocks.24.attn.qkv", | |
| "thinker.visual.blocks.24.attn.proj", | |
| "thinker.visual.blocks.24.mlp.linear_fc1", | |
| "thinker.visual.blocks.24.mlp.linear_fc2", | |
| "thinker.visual.blocks.25.attn.qkv", | |
| "thinker.visual.blocks.25.attn.proj", | |
| "thinker.visual.blocks.25.mlp.linear_fc1", | |
| "thinker.visual.blocks.25.mlp.linear_fc2", | |
| "thinker.visual.blocks.26.attn.qkv", | |
| "thinker.visual.blocks.26.attn.proj", | |
| "thinker.visual.blocks.26.mlp.linear_fc1", | |
| "thinker.visual.blocks.26.mlp.linear_fc2", | |
| "thinker.visual.merger.mlp.0", | |
| "thinker.visual.merger.mlp.2", | |
| "thinker.model.layers.0.mlp.gate", | |
| "thinker.model.layers.1.mlp.gate", | |
| "thinker.model.layers.2.mlp.gate", | |
| "thinker.model.layers.3.mlp.gate", | |
| "thinker.model.layers.4.mlp.gate", | |
| "thinker.model.layers.5.mlp.gate", | |
| "thinker.model.layers.6.mlp.gate", | |
| "thinker.model.layers.7.mlp.gate", | |
| "thinker.model.layers.8.mlp.gate", | |
| "thinker.model.layers.9.mlp.gate", | |
| "thinker.model.layers.10.mlp.gate", | |
| "thinker.model.layers.11.mlp.gate", | |
| "thinker.model.layers.12.mlp.gate", | |
| "thinker.model.layers.13.mlp.gate", | |
| "thinker.model.layers.14.mlp.gate", | |
| "thinker.model.layers.15.mlp.gate", | |
| "thinker.model.layers.16.mlp.gate", | |
| "thinker.model.layers.17.mlp.gate", | |
| "thinker.model.layers.18.mlp.gate", | |
| "thinker.model.layers.19.mlp.gate", | |
| "thinker.model.layers.20.mlp.gate", | |
| "thinker.model.layers.21.mlp.gate", | |
| "thinker.model.layers.22.mlp.gate", | |
| "thinker.model.layers.23.mlp.gate", | |
| "thinker.model.layers.24.mlp.gate", | |
| "thinker.model.layers.25.mlp.gate", | |
| "thinker.model.layers.26.mlp.gate", | |
| "thinker.model.layers.27.mlp.gate", | |
| "thinker.model.layers.28.mlp.gate", | |
| "thinker.model.layers.29.mlp.gate", | |
| "thinker.model.layers.30.mlp.gate", | |
| "thinker.model.layers.31.mlp.gate", | |
| "thinker.model.layers.32.mlp.gate", | |
| "thinker.model.layers.33.mlp.gate", | |
| "thinker.model.layers.34.mlp.gate", | |
| "thinker.model.layers.35.mlp.gate", | |
| "thinker.model.layers.36.mlp.gate", | |
| "thinker.model.layers.37.mlp.gate", | |
| "thinker.model.layers.38.mlp.gate", | |
| "thinker.model.layers.39.mlp.gate", | |
| "thinker.model.layers.40.mlp.gate", | |
| "thinker.model.layers.41.mlp.gate", | |
| "thinker.model.layers.42.mlp.gate", | |
| "thinker.model.layers.43.mlp.gate", | |
| "thinker.model.layers.44.mlp.gate", | |
| "thinker.model.layers.45.mlp.gate", | |
| "thinker.model.layers.46.mlp.gate", | |
| "thinker.model.layers.47.mlp.gate", | |
| "thinker.lm_head" | |
| ], | |
| "kv_cache_scheme": null, | |
| "quant_method": "compressed-tensors", | |
| "quantization_status": "compressed", | |
| "sparsity_config": {}, | |
| "transform_config": {}, | |
| "version": "0.11.0" | |
| }, | |
| "transformers_version": "4.57.0.dev0", | |
| "tts_bos_token_id": 151672, | |
| "tts_eos_token_id": 151673, | |
| "tts_pad_token_id": 151671, | |
| "user_token_id": 872 | |
| } | |