Upload folder using huggingface_hub

.gitattributes

@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 onnx/decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text
 onnx/decoder_model_merged_fp16.onnx_data filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -10,6 +10,7 @@
   "<quad>": 151668,
   "<ref>": 151670,
   "<tool_call>": 151657,
+  "<video>": 151674,
   "<|box_end|>": 151649,
   "<|box_start|>": 151648,
   "<|endoftext|>": 151643,

config.json

@@ -1,76 +1,30 @@
 {
-  "_commit_hash": null,
-  "_name_or_path": "OpenGVLab/InternVL3-2B",
+  "_name_or_path": "OpenGVLab/InternVL3-2B-hf",
   "architectures": [
-    "InternVLChatModel"
+    "InternVLForConditionalGeneration"
   ],
   "downsample_ratio": 0.5,
-  "dynamic_image_size": true,
-  "force_image_size": 448,
-  "hidden_size": 1536,
-  "image_fold": null,
-  "llm_config": {
-    "_attn_implementation_autoset": true,
-    "_name_or_path": "./pretrained/Qwen2.5-32B-Instruct",
-    "add_cross_attention": false,
+  "image_seq_length": 256,
+  "image_token_id": 151667,
+  "model_type": "internvl",
+  "projector_hidden_act": "gelu",
+  "text_config": {
     "architectures": [
       "Qwen2ForCausalLM"
     ],
     "attention_dropout": 0.0,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
     "bos_token_id": 151643,
-    "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": 151643,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
+    "eos_token_id": 151645,
     "hidden_act": "silu",
     "hidden_size": 1536,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
     "initializer_range": 0.02,
     "intermediate_size": 8960,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "length_penalty": 1.0,
-    "max_length": 20,
     "max_position_embeddings": 32768,
     "max_window_layers": 70,
-    "min_length": 0,
     "model_type": "qwen2",
-    "moe_config": null,
-    "no_repeat_ngram_size": 0,
     "num_attention_heads": 12,
-    "num_beam_groups": 1,
-    "num_beams": 1,
     "num_hidden_layers": 28,
     "num_key_value_heads": 2,
-    "num_return_sequences": 1,
-    "output_attentions": false,
-    "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,
     "rms_norm_eps": 1e-06,
     "rope_scaling": {
       "factor": 2.0,
@@ -78,142 +32,46 @@
       "type": "dynamic"
     },
     "rope_theta": 1000000.0,
-    "sep_token_id": null,
     "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,
     "torch_dtype": "bfloat16",
-    "torchscript": false,
-    "transformers_version": "4.48.3",
-    "typical_p": 1.0,
-    "use_bfloat16": true,
-    "use_cache": false,
+    "use_cache": true,
     "use_sliding_window": false,
     "vocab_size": 151674
   },
-  "max_dynamic_patch": 12,
-  "min_dynamic_patch": 1,
-  "model_type": "internvl_chat",
-  "pad2square": false,
-  "ps_version": "v2",
-  "select_layer": -1,
-  "system_message": null,
-  "template": "internvl2_5",
-  "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": null,
-  "use_backbone_lora": 0,
-  "use_llm_lora": 0,
-  "use_thumbnail": true,
+  "transformers_version": "4.52.0.dev0",
   "vision_config": {
-    "_attn_implementation_autoset": true,
-    "_name_or_path": "OpenGVLab/InternViT-6B-448px-V1-5",
-    "add_cross_attention": false,
     "architectures": [
       "InternVisionModel"
     ],
+    "attention_bias": true,
     "attention_dropout": 0.0,
-    "auto_map": {
-      "AutoConfig": "configuration_intern_vit.InternVisionConfig",
-      "AutoModel": "modeling_intern_vit.InternVisionModel"
-    },
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": null,
-    "capacity_factor": 1.2,
-    "chunk_size_feed_forward": 0,
-    "cross_attention_hidden_size": null,
-    "decoder_start_token_id": null,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "drop_path_rate": 0.1,
     "dropout": 0.0,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": null,
-    "eval_capacity_factor": 1.4,
-    "exponential_decay_length_penalty": null,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
     "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
     "hidden_size": 1024,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "image_size": 448,
+    "image_size": [
+      448,
+      448
+    ],
     "initializer_factor": 0.1,
     "initializer_range": 1e-10,
     "intermediate_size": 4096,
-    "is_decoder": false,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "laux_allreduce": "all_nodes",
     "layer_norm_eps": 1e-06,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "min_length": 0,
-    "model_type": "intern_vit_6b",
-    "moe_coeff_ratio": 0.5,
-    "moe_intermediate_size": 768,
-    "moe_output_scale": 4.0,
-    "no_repeat_ngram_size": 0,
-    "noisy_gate_policy": "RSample_before",
+    "layer_scale_init_value": 0.1,
+    "model_type": "internvl_vision",
     "norm_type": "layer_norm",
     "num_attention_heads": 16,
-    "num_beam_groups": 1,
-    "num_beams": 1,
     "num_channels": 3,
-    "num_experts": 8,
     "num_hidden_layers": 24,
-    "num_return_sequences": 1,
-    "num_routed_experts": 4,
-    "num_shared_experts": 4,
-    "output_attentions": false,
-    "output_hidden_states": false,
-    "output_scores": false,
-    "pad_token_id": null,
     "patch_size": 14,
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "qk_normalization": false,
-    "qkv_bias": true,
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "sep_token_id": null,
-    "shared_expert_intermediate_size": 3072,
-    "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,
+    "projection_dropout": 0.0,
     "torch_dtype": "bfloat16",
-    "torchscript": false,
-    "transformers_version": "4.48.3",
-    "typical_p": 1.0,
-    "use_bfloat16": true,
-    "use_flash_attn": true,
-    "use_moe": false,
-    "use_residual": true,
-    "use_rts": false,
-    "use_weighted_residual": false
-  }
+    "use_absolute_position_embeddings": true,
+    "use_mask_token": false,
+    "use_mean_pooling": true,
+    "use_qk_norm": false
+  },
+  "vision_feature_layer": -1,
+  "vision_feature_select_strategy": "default"
 }

generation_config.json

@@ -1,4 +1,6 @@
 {
   "_from_model_config": true,
-  "transformers_version": "4.48.3"
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "transformers_version": "4.52.0.dev0"
 }

onnx/decoder_model_merged.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b86d0f6387aff4168f5f8ea8ba138ab1f157f98f96725c884b32596ef681da2
-size 812416
+oid sha256:f020efc01cdfbe3c959d371dae9353794e3ec74122ef3a4446a9c20123dc1582
+size 1008073

onnx/decoder_model_merged_bnb4.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73fbf069a7de5ef7f3f06933349729d7939fa87bd1abfa13d0024d6a482996b6
-size 869427722
+oid sha256:effc3b5767679ed682e9ecb3669ee91d654dc42a7ab40768469b720e2f928f64
+size 869623343

onnx/decoder_model_merged_fp16.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b853540502c6a8172e2bd518601ba5d1404c82ab276c4ecf8b9e3aa66ead275c
-size 851104
+oid sha256:1498a0cfb4872c182079214a0dbce59a16821135dcb8ffb407b2890e63bdc2b8
+size 1046033

onnx/decoder_model_merged_int8.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4096dd92a63e1303f26fd20cea5ffbdc9ac79aa9bb806181178cd506569d3d6f
-size 1548732008
+oid sha256:c56a19d84d85782454046cf56a1be882a21ae575ee25d341a886f490e226bd18
+size 1548968535

onnx/decoder_model_merged_q4.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87433eb12033da23e7800b6e544bdcc6125d7d038fb819e981876cb66711a485
-size 965874026
+oid sha256:71ffb4bdfdb8a62278acb979d7edc2a1633bebc54337791888104393c4780417
+size 966069647

onnx/decoder_model_merged_q4f16.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:067af8e730d05fc1591c6c5ba992261b7229052c020160388df2bd391b938b3a
-size 869149396
+oid sha256:a16af4208f7acea05586a68fd8647bd020c03978abbefdd414f5098719300659
+size 869344323

onnx/decoder_model_merged_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4096dd92a63e1303f26fd20cea5ffbdc9ac79aa9bb806181178cd506569d3d6f
-size 1548732008
+oid sha256:c56a19d84d85782454046cf56a1be882a21ae575ee25d341a886f490e226bd18
+size 1548968535

onnx/decoder_model_merged_uint8.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7944385d44e1691acec4b522d23491ff97daf54f287d48f2466f7d61ee4ceb1e
-size 1548732008
+oid sha256:8dc0eeb12a3d5a29d86818b8fc998a5a30e5aa49b452c9c0867b176aa2b8dd19
+size 1548968535

onnx/embed_tokens.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdf81e17f9bec5199802212ca7e7667e14b1aa839727315bf40d41587b360c73
+oid sha256:fe1785d6723c5a6d174d6329d44760f36f43b68a7014bfe8702b592d4802b8be
 size 931885394

onnx/embed_tokens_bnb4.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba45088c4dec51d451460f9751c3635bd06ce80083b07d7e2a015116800605bb
+oid sha256:9e362b55fc08561241f7591fb2983ac6bd8ba14fd5eed8b5c4d4318e84c4e1e5
 size 931885413

onnx/embed_tokens_fp16.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05512597438cbe877479d1707397f08345beec9f3bda56233ecfb83f52a3803b
+oid sha256:2a025fdc951e69075017852821ed5e9d8771e759482384d6bdb09a4e7af3ae76
 size 465942894

onnx/embed_tokens_q4.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba45088c4dec51d451460f9751c3635bd06ce80083b07d7e2a015116800605bb
+oid sha256:9e362b55fc08561241f7591fb2983ac6bd8ba14fd5eed8b5c4d4318e84c4e1e5
 size 931885413

onnx/embed_tokens_q4f16.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4074de851bd10407a308c3769baa2d5a3c977ac8a3b0ec353c791c5e2b7b024
+oid sha256:deba2fabe018575a7b9b2f3119655cc5ce4c3655113442064ee18b0160e81058
 size 465942913

onnx/image_embeds.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91b7fdf672cb666540e58c78155793bcd85d6d656d6a9468c8a6540f692219a0
-size 1251170210
+oid sha256:b309189b0470bc37a5b171a4552be6322ba93ae03d98a331c3416763d0835ef3
+size 1251245175

onnx/image_embeds_bnb4.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:398c754150154676300c795d18fda1c7f079f7688dc0fbe38e2b0d6c311e5c31
-size 183358465
+oid sha256:74af480b5403ce4dbec7b5671d743669eec4b3b3bf98bcbc56a11c545402b480
+size 183440916

onnx/image_embeds_fp16.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac118eb4074905960e10a77dd6f3d0fdc5b795a12932728c329e826754fc270e
-size 627919100
+oid sha256:772e9f3d27390cff1c113e1997d1f55a2986c9ce73e9f1fea91c5b7ec2fca15f
+size 627994070

onnx/image_embeds_int8.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c16361e8c9ec130d0226569dfd2d016b74a3301dd8f9af6bf807d80b3f32a17b
-size 318695126
+oid sha256:74dfec899834faa47e9f8d035e0613aa72bb9e28712b874eed8a2bfe6638b301
+size 318835232

onnx/image_embeds_q4.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62115536ece81778f9388277b3ca19eb54de01c62578e972ff979fb0298f6a55
-size 202772697
+oid sha256:8225bd15503f8f9c69a25443c249d295b4b3a0f1868f0493606b96d49cc9515c
+size 202854764

onnx/image_embeds_q4f16.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2f75f24d5669e061be4fcb472a639249fa2d1890e6599b71490a6993c5ee397
-size 181387827
+oid sha256:a59391d8aeb7f20f6f22cae0a30ea26488a52efa526c33e4d69c242a365a290c
+size 181469899

onnx/image_embeds_quantized.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:155423eafc5f92ddd1b03c5e077f07622410c4e4f91bfcd921fef3052267ab78
-size 318695126
+oid sha256:066d908399a1ffc4f26831b51590313faa8f304600996646efc8c1023137ec54
+size 318835232

onnx/image_embeds_uint8.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:155423eafc5f92ddd1b03c5e077f07622410c4e4f91bfcd921fef3052267ab78
-size 318695126
+oid sha256:066d908399a1ffc4f26831b51590313faa8f304600996646efc8c1023137ec54
+size 318835232

special_tokens_map.json

@@ -12,8 +12,19 @@
     "<|vision_end|>",
     "<|vision_pad|>",
     "<|image_pad|>",
-    "<|video_pad|>"
+    "<|video_pad|>",
+    "<img>",
+    "</img>",
+    "<IMG_CONTEXT>",
+    "<quad>",
+    "</quad>",
+    "<ref>",
+    "</ref>",
+    "<box>",
+    "</box>"
   ],
+  "context_image_token": "<IMG_CONTEXT>",
+  "end_image_token": "</img>",
   "eos_token": {
     "content": "<|im_end|>",
     "lstrip": false,
@@ -27,5 +38,7 @@
     "normalized": false,
     "rstrip": false,
     "single_word": false
-  }
+  },
+  "start_image_token": "<img>",
+  "video_token": "<video>"
 }

tokenizer_config.json

@@ -1,6 +1,5 @@
 {
   "add_bos_token": false,
-  "add_eos_token": false,
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "151643": {
@@ -250,6 +249,14 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "151674": {
+      "content": "<video>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "additional_special_tokens": [
@@ -265,17 +272,35 @@
     "<|vision_end|>",
     "<|vision_pad|>",
     "<|image_pad|>",
-    "<|video_pad|>"
+    "<|video_pad|>",
+    "<img>",
+    "</img>",
+    "<IMG_CONTEXT>",
+    "<quad>",
+    "</quad>",
+    "<ref>",
+    "</ref>",
+    "<box>",
+    "</box>"
   ],
   "bos_token": null,
-  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
   "clean_up_tokenization_spaces": false,
+  "context_image_token": "<IMG_CONTEXT>",
+  "end_image_token": "</img>",
   "eos_token": "<|im_end|>",
   "errors": "replace",
-  "extra_special_tokens": {},
-  "model_max_length": 12288,
+  "extra_special_tokens": {
+    "context_image_token": "<IMG_CONTEXT>",
+    "end_image_token": "</img>",
+    "start_image_token": "<img>",
+    "video_token": "<video>"
+  },
+  "model_max_length": 8192,
   "pad_token": "<|endoftext|>",
+  "return_token_type_ids": false,
   "split_special_tokens": false,
+  "start_image_token": "<img>",
   "tokenizer_class": "Qwen2Tokenizer",
-  "unk_token": null
+  "unk_token": null,
+  "video_token": "<video>"
 }