commit a49b690d1cddba592752dc3df0a31addba460512 Author: ModelHub XC Date: Tue Jun 9 16:41:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: nanonets/Nanonets-OCR2-1.5B-exp Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..616295c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,55 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow 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 + +model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +merges.txt filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +trainer_state.json filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +training_args.bin 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..1c727a4 --- /dev/null +++ b/README.md @@ -0,0 +1,310 @@ +--- +language: +- multilingual +base_model: +- Qwen/Qwen2-VL-2B-Instruct +tags: +- OCR +- image-to-text +- pdf2markdown +- VQA +pipeline_tag: image-text-to-text +license: apache-2.0 +library_name: transformers +--- + + +
+

+ +

+

+Nanonets-OCR2: A model for transforming documents into structured markdown with intelligent content recognition and semantic tagging +

+ +
+ 🖥️ Live Demo | + 📢 Blog | + ⌨️ GitHub +
+ +
+ +Nanonets-OCR2 by [Nanonets](https://nanonets.com) is a family of powerful, state-of-the-art image-to-markdown OCR models that go far beyond traditional text extraction. It transforms documents into structured markdown with intelligent content recognition and semantic tagging, making it ideal for downstream processing by Large Language Models (LLMs). + +Nanonets-OCR2 is packed with features designed to handle complex documents with ease: + +* **LaTeX Equation Recognition:** Automatically converts mathematical equations and formulas into properly formatted LaTeX syntax. It distinguishes between inline (`$...$`) and display (`$$...$$`) equations. +* **Intelligent Image Description:** Describes images within documents using structured `` tags, making them digestible for LLM processing. It can describe various image types, including logos, charts, graphs and so on, detailing their content, style, and context. +* **Signature Detection & Isolation:** Identifies and isolates signatures from other text, outputting them within a `` tag. This is crucial for processing legal and business documents. +* **Watermark Extraction:** Detects and extracts watermark text from documents, placing it within a `` tag. +* **Smart Checkbox Handling:** Converts form checkboxes and radio buttons into standardized Unicode symbols (`☐`, `☑`, `☒`) for consistent and reliable processing. +* **Complex Table Extraction:** Accurately extracts complex tables from documents and converts them into both markdown and HTML table formats. +* **Flow charts & Organisational charts:** Extracts flow charts and organisational as [mermaid](mermaid.js.org) code. +* **Handwritten Documents:** The model is trained on handwritten documents across multiple languages. +* **Multilingual:** Model is trained on documents of multiple languages, including English, Chinese, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Arabic, and many more. +* **Visual Question Answering (VQA):** The model is designed to provide the answer directly if it is present in the document; otherwise, it responds with "Not mentioned." + + +## Nanonets-OCR2 Family +| Model | Access Link | +| -----|-----| +| Nanonets-OCR2-Plus | [Docstrange link](https://docstrange.nanonets.com/) | +| Nanonets-OCR2-3B | [🤗 link](https://huggingface.co/nanonets/Nanonets-OCR2-3B) | +| Nanonets-OCR2-1.5B-exp | [🤗 link](https://huggingface.co/nanonets/Nanonets-OCR2-1.5B-exp) | + + +## Usage +### Using transformers +```python +from PIL import Image +from transformers import AutoTokenizer, AutoProcessor, AutoModelForImageTextToText + +model_path = "nanonets/Nanonets-OCR2-3B" + +model = AutoModelForImageTextToText.from_pretrained( + model_path, + torch_dtype="auto", + device_map="auto", + attn_implementation="flash_attention_2" +) +model.eval() + +tokenizer = AutoTokenizer.from_pretrained(model_path) +processor = AutoProcessor.from_pretrained(model_path) + + +def ocr_page_with_nanonets_s(image_path, model, processor, max_new_tokens=4096): + prompt = """Extract the text from the above document as if you were reading it naturally. Return the tables in html format. Return the equations in LaTeX representation. If there is an image in the document and image caption is not present, add a small description of the image inside the tag; otherwise, add the image caption inside . Watermarks should be wrapped in brackets. Ex: OFFICIAL COPY. Page numbers should be wrapped in brackets. Ex: 14 or 9/22. Prefer using ☐ and ☑ for check boxes.""" + image = Image.open(image_path) + messages = [ + {"role": "system", "content": "You are a helpful assistant."}, + {"role": "user", "content": [ + {"type": "image", "image": f"file://{image_path}"}, + {"type": "text", "text": prompt}, + ]}, + ] + text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) + inputs = processor(text=[text], images=[image], padding=True, return_tensors="pt") + inputs = inputs.to(model.device) + + output_ids = model.generate(**inputs, max_new_tokens=max_new_tokens, do_sample=False) + generated_ids = [output_ids[len(input_ids):] for input_ids, output_ids in zip(inputs.input_ids, output_ids)] + + output_text = processor.batch_decode(generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=True) + return output_text[0] + +image_path = "/path/to/your/document.jpg" +result = ocr_page_with_nanonets_s(image_path, model, processor, max_new_tokens=15000) +print(result) +``` + +### Using vLLM +1. Start the vLLM server. +```bash +vllm serve nanonets/Nanonets-OCR2-3B +``` +2. Predict with the model +```python +from openai import OpenAI +import base64 + +client = OpenAI(api_key="123", base_url="http://localhost:8000/v1") + +model = "nanonets/Nanonets-OCR2-3B" + +def encode_image(image_path): + with open(image_path, "rb") as image_file: + return base64.b64encode(image_file.read()).decode("utf-8") + +def ocr_page_with_nanonets_s(img_base64): + response = client.chat.completions.create( + model=model, + messages=[ + { + "role": "user", + "content": [ + { + "type": "image_url", + "image_url": {"url": f"data:image/png;base64,{img_base64}"}, + }, + { + "type": "text", + "text": "Extract the text from the above document as if you were reading it naturally. Return the tables in html format. Return the equations in LaTeX representation. If there is an image in the document and image caption is not present, add a small description of the image inside the tag; otherwise, add the image caption inside . Watermarks should be wrapped in brackets. Ex: OFFICIAL COPY. Page numbers should be wrapped in brackets. Ex: 14 or 9/22. Prefer using ☐ and ☑ for check boxes.", + }, + ], + } + ], + temperature=0.0, + max_tokens=15000 + ) + return response.choices[0].message.content + +test_img_path = "/path/to/your/document.jpg" +img_base64 = encode_image(test_img_path) +print(ocr_page_with_nanonets_s(img_base64)) +``` + +### Using Docstrange + +```python +import requests + +url = "https://extraction-api.nanonets.com/extract" +headers = {"Authorization": } + +files = {"file": open("/path/to/your/file", "rb")} +data = {"output_type": "markdown"} +data["model"] = "nanonets" + +response = requests.post(url, headers=headers, files=files, data=data) +print(response.json()) +```` + +Check out [Docstrange](https://docstrange.nanonets.com/) for more details. + +## Evaluation +### Markdown Evaluations + +#### Nanonets OCR2 Plus + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
ModelWin Rate vs Nanonets OCR2 Plus (%)Lose Rate vs Nanonets OCR2 Plus (%)Both Correct (%)
Gemini 2.5 flash (No Thinking)34.3557.608.06
Nanonets OCR2 3B29.3754.5816.04
Nanonets-OCR-s24.8666.129.02
Nanonets OCR2 1.5B exp13.0081.205.79
GPT-5 (Thinking: low)23.5374.861.60
+ +#### Nanonets OCR2 3B + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
ModelWin Rate vs Nanonets OCR2 3B (%)Lose Rate vs Nanonets OCR2 3B (%)Both Correct (%)
Gemini 2.5 flash (No Thinking)39.9852.437.58
Nanonets-OCR-s30.6158.2811.12
Nanonets OCR2 1.5B exp14.7879.186.04
GPT-525.0072.872.13
+ +### Visual Question Answering (VQA) Evaluations + + + + + + + + + + + + + + + + + + + + + + + + + + +
DatasetNanonets OCR2 PlusNanonets OCR2 3BQwen2.5-VL-72B-InstructGemini 2.5 Flash
ChartQA (IDP-Leaderboard)79.2078.5676.2084.82
DocVQA (IDP-Leaderboard)85.1589.4384.0085.51
+ + +## Tips to improve accuracy +1. Increasing the image resolution will improve model's performance. +2. For complex tables (eg. Financial documents) using `repetition_penalty=1` gives better results. You can try this prompt also, which generally works better for finantial documents. +```python +user_prompt = """Extract the text from the above document as if you were reading it naturally. Return the tables in html format. Return the equations in LaTeX representation. If there is an image in the document and image caption is not present, add a small description of the image inside the tag; otherwise, add the image caption inside . Watermarks should be wrapped in brackets. Ex: OFFICIAL COPY. Page numbers should be wrapped in brackets. Ex: 14 or 9/22. Prefer using ☐ and ☑ for check boxes.""" +``` +3. This is already implemented in [Docstrange](https://docstrange.nanonets.com/?output_type=markdown-financial-docs), please use the `Markdown (Financial Docs)` option for processing table heavy financial documents. +```python +import requests + +url = "https://extraction-api.nanonets.com/extract" +headers = {"Authorization": } + +files = {"file": open("/path/to/your/file", "rb")} +data = {"output_type": "markdown-financial-docs"} + +response = requests.post(url, headers=headers, files=files, data=data) +print(response.json()) +``` + + +## BibTex +``` +@misc{Nanonets-OCR2, + title={Nanonets-OCR2: A model for transforming documents into structured markdown with intelligent content recognition and semantic tagging}, + author={Souvik Mandal and Ashish Talewar and Siddhant Thakuria and Paras Ahuja and Prathamesh Juvatkar}, + year={2025}, +} +``` \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..caa8130 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,16 @@ +{ + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|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..6c22663 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,7 @@ +{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system +You are a helpful assistant.<|im_end|> +{% endif %}<|im_start|>{{ message['role'] }} +{% if message['content'] is string %}{{ message['content'] }}<|im_end|> +{% 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 %}<|im_end|> +{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant +{% endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..80231ad --- /dev/null +++ b/config.json @@ -0,0 +1,115 @@ +{ + "architectures": [ + "Qwen2VLForConditionalGeneration" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 1536, + "image_token_id": 151655, + "initializer_range": 0.02, + "intermediate_size": 8960, + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen2_vl", + "num_attention_heads": 12, + "num_hidden_layers": 16, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "mrope_section": [ + 16, + 24, + 24 + ], + "rope_type": "default", + "type": "default" + }, + "rope_theta": 1000000.0, + "sliding_window": 32768, + "text_config": { + "architectures": [ + "Qwen2VLForConditionalGeneration" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 1536, + "image_token_id": null, + "initializer_range": 0.02, + "intermediate_size": 8960, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen2_vl_text", + "num_attention_heads": 12, + "num_hidden_layers": 16, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "mrope_section": [ + 16, + 24, + 24 + ], + "rope_type": "default", + "type": "default" + }, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "use_cache": false, + "use_sliding_window": false, + "video_token_id": null, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652, + "vision_token_id": 151654, + "vocab_size": 151936 + }, + "torch_dtype": "float32", + "transformers_version": "4.55.0", + "use_cache": false, + "use_sliding_window": false, + "video_token_id": 151656, + "vision_config": { + "depth": 32, + "embed_dim": 1280, + "hidden_act": "quick_gelu", + "hidden_size": 1536, + "in_channels": 3, + "in_chans": 3, + "initializer_range": 0.02, + "mlp_ratio": 4, + "model_type": "qwen2_vl", + "num_heads": 16, + "patch_size": 14, + "spatial_merge_size": 2, + "spatial_patch_size": 14, + "temporal_patch_size": 2, + "torch_dtype": "bfloat16" + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652, + "vision_token_id": 151654, + "vocab_size": 151936 +} 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..bf3e351 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 151643, + "eos_token_id": 151645, + "transformers_version": "4.55.0", + "use_cache": false +} 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..64ff8fc --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a71dfffbc7aa9c7a2e3692a80d9c5ac7abb9542b68e1e18824fcfccff8dcb66 +size 4982048792 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..83610f7 --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1e5404f9a2669aed8897832230044728dfd08a1aca46fde9bf43b16f8670dd4 +size 1607660616 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..a5f4821 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,593 @@ +{ + "metadata": { + "total_parameters": 1647411712, + "total_size": 6589646848 + }, + "weight_map": { + "model.embed_tokens.weight": "model-00001-of-00002.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", + "model.norm.weight": "model-00002-of-00002.safetensors", + "visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.0.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.0.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.0.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.0.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.1.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.1.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.1.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.1.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.10.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.10.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.10.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.10.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.11.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.11.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.11.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.11.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.12.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.12.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.12.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.12.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.13.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.13.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.13.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.13.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.14.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.14.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.14.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.14.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.15.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.15.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.15.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.15.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.16.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.16.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.16.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.16.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.17.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.17.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.17.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.17.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.18.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.18.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.18.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.18.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.19.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.19.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.19.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.19.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.2.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.2.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.2.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.2.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.20.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.20.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.20.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.20.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.21.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.21.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.21.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.21.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.22.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.22.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.22.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.22.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.23.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.23.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.23.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.23.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.24.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.24.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.24.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.24.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.24.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.24.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.25.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.25.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.25.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.25.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.25.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.25.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.26.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.26.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.26.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.26.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.26.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.26.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.27.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.27.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.27.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.27.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.27.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.27.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.28.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.28.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.28.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.28.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.28.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.28.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.29.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.29.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.29.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.29.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.29.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.29.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.3.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.3.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.3.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.3.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.30.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.30.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.30.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.30.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.30.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.30.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.31.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.31.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.31.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.31.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.31.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.31.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.4.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.4.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.4.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.4.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.5.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.5.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.5.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.5.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.6.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.6.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.6.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.6.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.7.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.7.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.7.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.7.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.8.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.8.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.8.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.8.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors", + "visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors", + "visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors", + "visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors", + "visual.blocks.9.mlp.fc1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.9.mlp.fc1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.9.mlp.fc2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.9.mlp.fc2.weight": "model-00001-of-00002.safetensors", + "visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors", + "visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors", + "visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors", + "visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors", + "visual.merger.ln_q.bias": "model-00001-of-00002.safetensors", + "visual.merger.ln_q.weight": "model-00001-of-00002.safetensors", + "visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors", + "visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors", + "visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors", + "visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors", + "visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors" + } +} diff --git a/preprocessor_config.json b/preprocessor_config.json new file mode 100644 index 0000000..14a7104 --- /dev/null +++ b/preprocessor_config.json @@ -0,0 +1,37 @@ +{ + "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_rescale": true, + "do_resize": true, + "image_mean": [ + 0.48145466, + 0.4578275, + 0.40821073 + ], + "image_processor_type": "Qwen2VLImageProcessorFast", + "image_std": [ + 0.26862954, + 0.26130258, + 0.27577711 + ], + "input_data_format": null, + "max_pixels": 12845056, + "merge_size": 2, + "min_pixels": 3136, + "patch_size": 14, + "processor_class": "Qwen2VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "return_tensors": null, + "size": { + "longest_edge": 12845056, + "shortest_edge": 3136 + }, + "temporal_patch_size": 2 +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..ac23c0a --- /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": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..dcd1dbd --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a +size 11420371 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..c792a41 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,144 @@ +{ + "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 + } + }, + "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": 32768, + "pad_token": "<|endoftext|>", + "padding_side": "right", + "processor_class": "Qwen2VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000..863dc28 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4668c474490ea4e548e2345b97e2db0d17de07e02cf4487e446e63f8bfb94bb7 +size 1707563 diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..43f6fa9 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b147bab3a89ba3d252059dcdd4b348c1b830d038e84541218742ca41888c184 +size 6225 diff --git a/video_preprocessor_config.json b/video_preprocessor_config.json new file mode 100644 index 0000000..5258b25 --- /dev/null +++ b/video_preprocessor_config.json @@ -0,0 +1,43 @@ +{ + "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_pad": null, + "do_rescale": true, + "do_resize": true, + "do_sample_frames": false, + "fps": null, + "image_mean": [ + 0.48145466, + 0.4578275, + 0.40821073 + ], + "image_std": [ + 0.26862954, + 0.26130258, + 0.27577711 + ], + "input_data_format": null, + "max_frames": 768, + "max_pixels": 12845056, + "merge_size": 2, + "min_frames": 4, + "min_pixels": 3136, + "num_frames": null, + "patch_size": 14, + "processor_class": "Qwen2VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "size": { + "longest_edge": 12845056, + "shortest_edge": 3136 + }, + "size_divisor": null, + "temporal_patch_size": 2, + "video_metadata": null, + "video_processor_type": "Qwen2VLVideoProcessor" +} 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