commit 43751cae0434e5eca680881b48fb3e4e78be125a Author: ModelHub XC Date: Fri Jun 5 14:42:14 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: unsloth/Qwen3-VL-4B-Instruct Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1b7026b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,53 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +tokenizer.json filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +merges.txt filter=lfs diff=lfs merge=lfs -text +model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..deb80f9 --- /dev/null +++ b/README.md @@ -0,0 +1,217 @@ +--- +tags: +- unsloth +base_model: +- Qwen/Qwen3-VL-4B-Instruct +license: apache-2.0 +pipeline_tag: image-text-to-text +library_name: transformers +--- +> [!NOTE] +> Includes Unsloth **chat template fixes**!
For `llama.cpp`, use `--jinja` +> + +
+

+ Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants. +

+
+ + + + + + + + + +
+
+ + + Chat + + + +# Qwen3-VL-4B-Instruct + + +Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. + +This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities. + +Available in Dense and MoE architectures that scale from edge to cloud, with Instruct and reasoning‑enhanced Thinking editions for flexible, on‑demand deployment. + + +#### Key Enhancements: + +* **Visual Agent**: Operates PC/mobile GUIs—recognizes elements, understands functions, invokes tools, completes tasks. + +* **Visual Coding Boost**: Generates Draw.io/HTML/CSS/JS from images/videos. + +* **Advanced Spatial Perception**: Judges object positions, viewpoints, and occlusions; provides stronger 2D grounding and enables 3D grounding for spatial reasoning and embodied AI. + +* **Long Context & Video Understanding**: Native 256K context, expandable to 1M; handles books and hours-long video with full recall and second-level indexing. + +* **Enhanced Multimodal Reasoning**: Excels in STEM/Math—causal analysis and logical, evidence-based answers. + +* **Upgraded Visual Recognition**: Broader, higher-quality pretraining is able to “recognize everything”—celebrities, anime, products, landmarks, flora/fauna, etc. + +* **Expanded OCR**: Supports 32 languages (up from 19); robust in low light, blur, and tilt; better with rare/ancient characters and jargon; improved long-document structure parsing. + +* **Text Understanding on par with pure LLMs**: Seamless text–vision fusion for lossless, unified comprehension. + + +#### Model Architecture Updates: + +

+ +

+ + +1. **Interleaved-MRoPE**: Full‑frequency allocation over time, width, and height via robust positional embeddings, enhancing long‑horizon video reasoning. + +2. **DeepStack**: Fuses multi‑level ViT features to capture fine‑grained details and sharpen image–text alignment. + +3. **Text–Timestamp Alignment:** Moves beyond T‑RoPE to precise, timestamp‑grounded event localization for stronger video temporal modeling. + +This is the weight repository for Qwen3-VL-4B-Instruct. + + +--- + +## Model Performance + +**Multimodal performance** + +![](https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3-VL/qwen3vl_4b_8b_vl_instruct.jpg) + +**Pure text performance** +![](https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3-VL/qwen3vl_4b_8b_text_instruct.jpg) + +## Quickstart + +Below, we provide simple examples to show how to use Qwen3-VL with 🤖 ModelScope and 🤗 Transformers. + +The code of Qwen3-VL has been in the latest Hugging Face transformers and we advise you to build from source with command: +``` +pip install git+https://github.com/huggingface/transformers +# pip install transformers==4.57.0 # currently, V4.57.0 is not released +``` + +### Using 🤗 Transformers to Chat + +Here we show a code snippet to show how to use the chat model with `transformers`: + +```python +from transformers import Qwen3VLForConditionalGeneration, AutoProcessor + +# default: Load the model on the available device(s) +model = Qwen3VLForConditionalGeneration.from_pretrained( + "Qwen/Qwen3-VL-4B-Instruct", dtype="auto", device_map="auto" +) + +# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios. +# model = Qwen3VLForConditionalGeneration.from_pretrained( +# "Qwen/Qwen3-VL-4B-Instruct", +# dtype=torch.bfloat16, +# attn_implementation="flash_attention_2", +# device_map="auto", +# ) + +processor = AutoProcessor.from_pretrained("Qwen/Qwen3-VL-4B-Instruct") + +messages = [ + { + "role": "user", + "content": [ + { + "type": "image", + "image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg", + }, + {"type": "text", "text": "Describe this image."}, + ], + } +] + +# Preparation for inference +inputs = processor.apply_chat_template( + messages, + tokenize=True, + add_generation_prompt=True, + return_dict=True, + return_tensors="pt" +) +inputs = inputs.to(model.device) + +# Inference: Generation of the output +generated_ids = model.generate(**inputs, max_new_tokens=128) +generated_ids_trimmed = [ + out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids) +] +output_text = processor.batch_decode( + generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False +) +print(output_text) +``` + +### Generation Hyperparameters +#### VL +```bash +export greedy='false' +export top_p=0.8 +export top_k=20 +export temperature=0.7 +export repetition_penalty=1.0 +export presence_penalty=1.5 +export out_seq_length=16384 +``` + +#### Text +```bash +export greedy='false' +export top_p=1.0 +export top_k=40 +export repetition_penalty=1.0 +export presence_penalty=2.0 +export temperature=1.0 +export out_seq_length=32768 +``` + + +## Citation + +If you find our work helpful, feel free to give us a cite. + +``` +@misc{qwen3technicalreport, + title={Qwen3 Technical Report}, + author={Qwen Team}, + year={2025}, + eprint={2505.09388}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2505.09388}, +} + +@article{Qwen2.5-VL, + title={Qwen2.5-VL Technical Report}, + author={Bai, Shuai and Chen, Keqin and Liu, Xuejing and Wang, Jialin and Ge, Wenbin and Song, Sibo and Dang, Kai and Wang, Peng and Wang, Shijie and Tang, Jun and Zhong, Humen and Zhu, Yuanzhi and Yang, Mingkun and Li, Zhaohai and Wan, Jianqiang and Wang, Pengfei and Ding, Wei and Fu, Zheren and Xu, Yiheng and Ye, Jiabo and Zhang, Xi and Xie, Tianbao and Cheng, Zesen and Zhang, Hang and Yang, Zhibo and Xu, Haiyang and Lin, Junyang}, + journal={arXiv preprint arXiv:2502.13923}, + year={2025} +} + +@article{Qwen2VL, + title={Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution}, + author={Wang, Peng and Bai, Shuai and Tan, Sinan and Wang, Shijie and Fan, Zhihao and Bai, Jinze and Chen, Keqin and Liu, Xuejing and Wang, Jialin and Ge, Wenbin and Fan, Yang and Dang, Kai and Du, Mengfei and Ren, Xuancheng and Men, Rui and Liu, Dayiheng and Zhou, Chang and Zhou, Jingren and Lin, Junyang}, + journal={arXiv preprint arXiv:2409.12191}, + year={2024} +} + +@article{Qwen-VL, + title={Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond}, + author={Bai, Jinze and Bai, Shuai and Yang, Shusheng and Wang, Shijie and Tan, Sinan and Wang, Peng and Lin, Junyang and Zhou, Chang and Zhou, Jingren}, + journal={arXiv preprint arXiv:2308.12966}, + year={2023} +} +``` \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..b54f913 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,28 @@ +{ + "": 151668, + "": 151658, + "": 151666, + "": 151667, + "": 151657, + "": 151665, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..1243868 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,120 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].role == 'system' %} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n\n' }} + {%- endif %} + {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0].role == 'system' %} + {{- '<|im_start|>system\n' }} + {%- if messages[0].content is string %} + {{- messages[0].content }} + {%- else %} + {%- for content in messages[0].content %} + {%- if 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- set image_count = namespace(value=0) %} +{%- set video_count = namespace(value=0) %} +{%- for message in messages %} + {%- if message.role == "user" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role + '\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content_item in message.content %} + {%- if 'text' in content_item %} + {{- content_item.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {%- if message.tool_calls %} + {%- for tool_call in message.tool_calls %} + {%- if (loop.first and message.content) or (not loop.first) %} + {{- '\n' }} + {%- endif %} + {%- if tool_call.function %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {%- if tool_call.arguments is string %} + {{- tool_call.arguments }} + {%- else %} + {{- tool_call.arguments | tojson }} + {%- endif %} + {{- '}\n' }} + {%- endfor %} + {%- endif %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {%- if message.content is string %} + {{- message.content }} + {%- else %} + {%- for content in message.content %} + {%- if content.type == 'image' or 'image' in content or 'image_url' in content %} + {%- set image_count.value = image_count.value + 1 %} + {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%} + <|vision_start|><|image_pad|><|vision_end|> + {%- elif content.type == 'video' or 'video' in content %} + {%- set video_count.value = video_count.value + 1 %} + {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%} + <|vision_start|><|video_pad|><|vision_end|> + {%- elif 'text' in content %} + {{- content.text }} + {%- endif %} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/chat_template.json b/chat_template.json new file mode 100644 index 0000000..e49e75b --- /dev/null +++ b/chat_template.json @@ -0,0 +1,4 @@ +{ + "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within XML tags:\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{\\\"name\\\": , \\\"arguments\\\": }\\n<|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n' }}\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" +} + \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..3fabcf3 --- /dev/null +++ b/config.json @@ -0,0 +1,65 @@ +{ + "architectures": [ + "Qwen3VLForConditionalGeneration" + ], + "image_token_id": 151655, + "model_type": "qwen3_vl", + "pad_token_id": 151654, + "text_config": { + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 151643, + "torch_dtype": "bfloat16", + "eos_token_id": 151645, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 9728, + "max_position_embeddings": 262144, + "model_type": "qwen3_vl_text", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "mrope_interleaved": true, + "mrope_section": [ + 24, + 20, + 20 + ], + "rope_type": "default" + }, + "rope_theta": 5000000, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 151936 + }, + "tie_word_embeddings": true, + "transformers_version": "4.57.1", + "unsloth_fixed": true, + "video_token_id": 151656, + "vision_config": { + "deepstack_visual_indexes": [ + 5, + 11, + 17 + ], + "depth": 24, + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1024, + "in_channels": 3, + "initializer_range": 0.02, + "intermediate_size": 4096, + "model_type": "qwen3_vl", + "num_heads": 16, + "num_position_embeddings": 2304, + "out_hidden_size": 2560, + "patch_size": 16, + "spatial_merge_size": 2, + "temporal_patch_size": 2 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652 +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..4aef15d --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "image-text-to-text", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..e116347 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 151643, + "pad_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "top_k": 20, + "top_p": 0.8, + "repetition_penalty": 1.0, + "temperature": 0.7, + "transformers_version": "4.56.0" +} \ No newline at end of file diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..c76bab6 --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30a01a0556622645a3cce87b655bbbbbc1f170c196099f1b666c93202c3339a9 +size 4967229296 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..e2792fe --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:046296a2a387efb43b0c997d5833c789604d168834f6e0d3064bf7bb13d002a6 +size 3908490048 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..3b52de9 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,720 @@ +{ + "metadata": { + "total_size": 8875631616 + }, + "weight_map": { + "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.language_model.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.0.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.1.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.10.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.11.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.12.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.13.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.14.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.2.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.3.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.4.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.5.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.6.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.7.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.8.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm1.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm1.weight": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm2.bias": "model-00002-of-00002.safetensors", + "model.visual.blocks.9.norm2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.1.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors", + "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors", + "model.visual.merger.norm.weight": "model-00002-of-00002.safetensors", + "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors", + "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors", + "model.visual.pos_embed.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/preprocessor_config.json b/preprocessor_config.json new file mode 100644 index 0000000..2fa6553 --- /dev/null +++ b/preprocessor_config.json @@ -0,0 +1,39 @@ +{ + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "disable_grouping": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_pad": null, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_processor_type": "Qwen2VLImageProcessorFast", + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_pixels": null, + "merge_size": 2, + "min_pixels": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_tensors": null, + "size": { + "longest_edge": 16777216, + "shortest_edge": 65536 + }, + "temporal_patch_size": 2 +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..9b8043f --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..cd71f61 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..15f9248 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,242 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151665": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151666": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151667": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151668": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 262144, + "pad_token": "<|vision_pad|>", + "padding_side": "left", + "processor_class": "Qwen3VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null, + "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within XML tags:\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{\\\"name\\\": , \\\"arguments\\\": }\\n<|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].content is string %}\n {{- messages[0].content }}\n {%- else %}\n {%- for content in messages[0].content %}\n {%- if 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- for message in messages %}\n {%- if message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role + '\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content_item in message.content %}\n {%- if 'text' in content_item %}\n {{- content_item.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and message.content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {%- if message.content is string %}\n {{- message.content }}\n {%- else %}\n {%- for content in message.content %}\n {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}\n <|vision_start|><|image_pad|><|vision_end|>\n {%- elif content.type == 'video' or 'video' in content %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}\n <|vision_start|><|video_pad|><|vision_end|>\n {%- elif 'text' in content %}\n {{- content.text }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n {{- '\\n' }}\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" +} \ No newline at end of file diff --git a/video_preprocessor_config.json b/video_preprocessor_config.json new file mode 100644 index 0000000..e32b1d9 --- /dev/null +++ b/video_preprocessor_config.json @@ -0,0 +1,41 @@ +{ + "crop_size": null, + "data_format": "channels_first", + "default_to_square": true, + "device": null, + "do_center_crop": null, + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": true, + "fps": 2, + "image_mean": [ + 0.5, + 0.5, + 0.5 + ], + "image_std": [ + 0.5, + 0.5, + 0.5 + ], + "input_data_format": null, + "max_frames": 768, + "merge_size": 2, + "min_frames": 4, + "num_frames": null, + "pad_size": null, + "patch_size": 16, + "processor_class": "Qwen3VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_metadata": false, + "size": { + "longest_edge": 25165824, + "shortest_edge": 4096 + }, + "temporal_patch_size": 2, + "video_metadata": null, + "video_processor_type": "Qwen3VLVideoProcessor" +} diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833