Upload folder using huggingface_hub
Browse files- README.md +228 -0
- added_tokens.json +33 -0
- chat_template.json +3 -0
- config.json +52 -0
- generation_config.json +15 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- preprocessor_config.json +19 -0
- special_tokens_map.json +228 -0
- tokenizer.json +0 -0
- tokenizer_config.json +296 -0
- video_preprocessor_config.json +19 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,228 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: agpl-3.0
|
| 3 |
+
language:
|
| 4 |
+
- zh
|
| 5 |
+
- en
|
| 6 |
+
pipeline_tag: image-text-to-text
|
| 7 |
+
library_name: transformers
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
<div align="center">
|
| 12 |
+
|
| 13 |
+
<p align="center">
|
| 14 |
+
<img src="https://raw.githubusercontent.com/opendatalab/MinerU/master/docs/images/MinerU-logo.png" width="300"/>
|
| 15 |
+
<p>
|
| 16 |
+
|
| 17 |
+
<h1 align="center" style="font-size: 28px">
|
| 18 |
+
MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing
|
| 19 |
+
</h1>
|
| 20 |
+
|
| 21 |
+
[](https://github.com/opendatalab/MinerU/)
|
| 22 |
+
[](https://huggingface.co/opendatalab/MinerU2.5-2509-1.2B)
|
| 23 |
+
[](https://modelscope.cn/models/OpenDataLab/MinerU2.5-2509-1.2B)
|
| 24 |
+
[](https://huggingface.co/spaces/opendatalab/MinerU)
|
| 25 |
+
[](https://www.modelscope.cn/studios/OpenDataLab/MinerU)
|
| 26 |
+
|
| 27 |
+
|
| 28 |
+
<div align="center">
|
| 29 |
+
<a href="https://mineru.net/OpenSourceTools/Extractor" target="_blank" rel="noopener noreferrer"><strong>🚀 Official Demo</strong></a> |
|
| 30 |
+
<a href="https://arxiv.org/abs/2509.22186" target="_blank" rel="noopener noreferrer"><strong>📄 Technical Report</strong></a>
|
| 31 |
+
</div>
|
| 32 |
+
|
| 33 |
+
</div>
|
| 34 |
+
|
| 35 |
+
---
|
| 36 |
+
|
| 37 |
+
<p align="center">
|
| 38 |
+
<img alt="Image" src="https://hotelll.github.io/MinerU2.5/performance.jpeg"/>
|
| 39 |
+
<p>
|
| 40 |
+
|
| 41 |
+
# Introduction
|
| 42 |
+
<!-- We present **MinerU2.5**, a 1.2B-parameter VLM-based document parsing model that delivers state-of-the-art accuracy with high efficiency. It adopts a coarse-to-fine, two-stage parsing strategy. A large-scale, diverse data engine supports both pretraining and fine-tuning, enabling robust performance across document types. -->
|
| 43 |
+
**MinerU2.5** is a 1.2B-parameter vision-language model for document parsing that achieves state-of-the-art accuracy with high computational efficiency. It adopts a two-stage parsing strategy: first conducting efficient global layout analysis on downsampled images, then performing fine-grained content recognition on native-resolution crops for text, formulas, and tables. Supported by a large-scale, diverse data engine for pretraining and fine-tuning, MinerU2.5 consistently outperforms both general-purpose and domain-specific models across multiple benchmarks while maintaining low computational overhead.
|
| 44 |
+
|
| 45 |
+
## Key Improvements
|
| 46 |
+
<!-- - **More Precise Layout Detection:** Faithfully preserves non-body elements such as headers, footers, and page numbers, ensuring comprehensive content integrity.
|
| 47 |
+
- **Significantly Improved Body Text Recognition:** Produces more standardized text formatting with clearly discernible structures for lists, references, and other elements.
|
| 48 |
+
- **Breakthroughs in Formula Parsing:** Delivers high-quality parsing of complex, lengthy mathematical formulae and accurately recognizes mixed-language (Chinese-English) equations.
|
| 49 |
+
- **Enhanced Robustness in Table Parsing:** Effortlessly handles challenging cases, including rotated tables, borderless tables, and tables with partial borders. -->
|
| 50 |
+
|
| 51 |
+
- **Comprehensive and Granular Layout Analysis:** It not only preserves non-body elements like headers, footers, and page numbers to ensure full content integrity, but also employs a refined and standardized labeling schema. This enables a clearer, more structured representation of elements such as lists, references, and code blocks.
|
| 52 |
+
- **Breakthroughs in Formula Parsing:** Delivers high-quality parsing of complex, lengthy mathematical formulae and accurately recognizes mixed-language (Chinese-English) equations.
|
| 53 |
+
- **Enhanced Robustness in Table Parsing:** Effortlessly handles challenging cases, including rotated tables, borderless tables, and tables with partial borders.
|
| 54 |
+
|
| 55 |
+
|
| 56 |
+
# Quick Start
|
| 57 |
+
For convenience, we provide `mineru-vl-utils`, a Python package that simplifies the process of sending requests and handling responses from MinerU2.5 Vision-Language Model. Here we give some examples to use MinerU2.5. For more information and usages, please refer to [mineru-vl-utils](https://github.com/opendatalab/mineru-vl-utils/tree/main).
|
| 58 |
+
|
| 59 |
+
📌 We strongly recommend using vllm for inference, as the `vllm-async-engine` can achieve a concurrent inference speed of **2.12 fps** on one A100.
|
| 60 |
+
|
| 61 |
+
## Install packages
|
| 62 |
+
```bash
|
| 63 |
+
# For `transformers` backend
|
| 64 |
+
pip install "mineru-vl-utils[transformers]"
|
| 65 |
+
# For `vllm-engine` and `vllm-async-engine` backend
|
| 66 |
+
pip install "mineru-vl-utils[vllm]"
|
| 67 |
+
```
|
| 68 |
+
|
| 69 |
+
## `transformers` Example
|
| 70 |
+
|
| 71 |
+
```python
|
| 72 |
+
from transformers import AutoProcessor, Qwen2VLForConditionalGeneration
|
| 73 |
+
from PIL import Image
|
| 74 |
+
from mineru_vl_utils import MinerUClient
|
| 75 |
+
|
| 76 |
+
# for transformers>=4.56.0
|
| 77 |
+
model = Qwen2VLForConditionalGeneration.from_pretrained(
|
| 78 |
+
"opendatalab/MinerU2.5-2509-1.2B",
|
| 79 |
+
dtype="auto", # use `torch_dtype` instead of `dtype` for transformers<4.56.0
|
| 80 |
+
device_map="auto"
|
| 81 |
+
)
|
| 82 |
+
|
| 83 |
+
processor = AutoProcessor.from_pretrained(
|
| 84 |
+
"opendatalab/MinerU2.5-2509-1.2B",
|
| 85 |
+
use_fast=True
|
| 86 |
+
)
|
| 87 |
+
|
| 88 |
+
client = MinerUClient(
|
| 89 |
+
backend="transformers",
|
| 90 |
+
model=model,
|
| 91 |
+
processor=processor
|
| 92 |
+
)
|
| 93 |
+
|
| 94 |
+
image = Image.open("/path/to/the/test/image.png")
|
| 95 |
+
extracted_blocks = client.two_step_extract(image)
|
| 96 |
+
print(extracted_blocks)
|
| 97 |
+
```
|
| 98 |
+
|
| 99 |
+
## `vllm-engine` Example (Recommended!)
|
| 100 |
+
|
| 101 |
+
```python
|
| 102 |
+
from vllm import LLM
|
| 103 |
+
from PIL import Image
|
| 104 |
+
from mineru_vl_utils import MinerUClient
|
| 105 |
+
from mineru_vl_utils import MinerULogitsProcessor # if vllm>=0.10.1
|
| 106 |
+
|
| 107 |
+
llm = LLM(
|
| 108 |
+
model="opendatalab/MinerU2.5-2509-1.2B",
|
| 109 |
+
logits_processors=[MinerULogitsProcessor] # if vllm>=0.10.1
|
| 110 |
+
)
|
| 111 |
+
|
| 112 |
+
client = MinerUClient(
|
| 113 |
+
backend="vllm-engine",
|
| 114 |
+
vllm_llm=llm
|
| 115 |
+
)
|
| 116 |
+
|
| 117 |
+
image = Image.open("/path/to/the/test/image.png")
|
| 118 |
+
extracted_blocks = client.two_step_extract(image)
|
| 119 |
+
print(extracted_blocks)
|
| 120 |
+
```
|
| 121 |
+
|
| 122 |
+
## `vllm-async-engine` Example (Recommended!)
|
| 123 |
+
|
| 124 |
+
```python
|
| 125 |
+
import io
|
| 126 |
+
import asyncio
|
| 127 |
+
import aiofiles
|
| 128 |
+
|
| 129 |
+
from vllm.v1.engine.async_llm import AsyncLLM
|
| 130 |
+
from vllm.engine.arg_utils import AsyncEngineArgs
|
| 131 |
+
from PIL import Image
|
| 132 |
+
from mineru_vl_utils import MinerUClient
|
| 133 |
+
from mineru_vl_utils import MinerULogitsProcessor # if vllm>=0.10.1
|
| 134 |
+
|
| 135 |
+
async_llm = AsyncLLM.from_engine_args(
|
| 136 |
+
AsyncEngineArgs(
|
| 137 |
+
model="opendatalab/MinerU2.5-2509-1.2B",
|
| 138 |
+
logits_processors=[MinerULogitsProcessor] # if vllm>=0.10.1
|
| 139 |
+
)
|
| 140 |
+
)
|
| 141 |
+
|
| 142 |
+
client = MinerUClient(
|
| 143 |
+
backend="vllm-async-engine",
|
| 144 |
+
vllm_async_llm=async_llm,
|
| 145 |
+
)
|
| 146 |
+
|
| 147 |
+
async def main():
|
| 148 |
+
image_path = "/path/to/the/test/image.png"
|
| 149 |
+
async with aiofiles.open(image_path, "rb") as f:
|
| 150 |
+
image_data = await f.read()
|
| 151 |
+
image = Image.open(io.BytesIO(image_data))
|
| 152 |
+
extracted_blocks = await client.aio_two_step_extract(image)
|
| 153 |
+
print(extracted_blocks)
|
| 154 |
+
|
| 155 |
+
asyncio.run(main())
|
| 156 |
+
|
| 157 |
+
async_llm.shutdown()
|
| 158 |
+
```
|
| 159 |
+
|
| 160 |
+
# Model Architecture
|
| 161 |
+
<p align="center">
|
| 162 |
+
<img alt="Image" src="https://hotelll.github.io/MinerU2.5/Mineru25_framework.jpeg"/>
|
| 163 |
+
<p>
|
| 164 |
+
|
| 165 |
+
# Performance on OmniDocBench
|
| 166 |
+
## Across Different Elements
|
| 167 |
+
<p align="center">
|
| 168 |
+
<img alt="Image" src="https://hotelll.github.io/MinerU2.5/omnidocbench_element.jpeg"/>
|
| 169 |
+
<p>
|
| 170 |
+
|
| 171 |
+
## Across Various Document Types
|
| 172 |
+
<p align="center">
|
| 173 |
+
<img alt="Image" src="https://hotelll.github.io/MinerU2.5/omnidocbench_type.jpeg"/>
|
| 174 |
+
<p>
|
| 175 |
+
|
| 176 |
+
|
| 177 |
+
# Case Demonstration
|
| 178 |
+
## Full-Document Parsing across Various Doc-Types
|
| 179 |
+
<p align="center">
|
| 180 |
+
<img alt="Image" src="https://hotelll.github.io/MinerU2.5/PDF-Type-1_page_1.png"/>
|
| 181 |
+
<p>
|
| 182 |
+
|
| 183 |
+
<p align="center">
|
| 184 |
+
<img alt="Image" src="https://hotelll.github.io/MinerU2.5/PDF-Type-2_page_1.png"/>
|
| 185 |
+
<p>
|
| 186 |
+
|
| 187 |
+
<p align="center">
|
| 188 |
+
<img alt="Image" src="https://hotelll.github.io/MinerU2.5//PDF-Type-3_page_1.png"/>
|
| 189 |
+
<p>
|
| 190 |
+
|
| 191 |
+
## Table Recognition
|
| 192 |
+
<p align="center">
|
| 193 |
+
<img alt="Image" src="https://hotelll.github.io/MinerU2.5/Table-Module-1_page_1.png"/>
|
| 194 |
+
<p>
|
| 195 |
+
|
| 196 |
+
<p align="center">
|
| 197 |
+
<img alt="Image" src="https://hotelll.github.io/MinerU2.5/Table-Module-2_page_1.png"/>
|
| 198 |
+
<p>
|
| 199 |
+
|
| 200 |
+
## Formula Recognition
|
| 201 |
+
<p align="center">
|
| 202 |
+
<img alt="Image" src="https://hotelll.github.io/MinerU2.5/Formula-Module-1_page_1.png"/>
|
| 203 |
+
<p>
|
| 204 |
+
|
| 205 |
+
<p align="center">
|
| 206 |
+
<img alt="Image" src="https://hotelll.github.io/MinerU2.5/Formula-Module-2_page_1.png"/>
|
| 207 |
+
<p>
|
| 208 |
+
|
| 209 |
+
|
| 210 |
+
# Acknowledgements
|
| 211 |
+
We would like to thank [Qwen Team](https://github.com/QwenLM), [vLLM](https://github.com/vllm-project/vllm), [OmniDocBench](https://github.com/opendatalab/OmniDocBench), [UniMERNet](https://github.com/opendatalab/UniMERNet), [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR), [DocLayout-YOLO](https://github.com/opendatalab/DocLayout-YOLO) for providing valuable code and models. We also appreciate everyone's contribution to this open-source project!
|
| 212 |
+
|
| 213 |
+
|
| 214 |
+
# Citation
|
| 215 |
+
|
| 216 |
+
If you find our work useful in your research, please consider giving a star ⭐ and citation 📝 :
|
| 217 |
+
|
| 218 |
+
```BibTeX
|
| 219 |
+
@misc{niu2025mineru25decoupledvisionlanguagemodel,
|
| 220 |
+
title={MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing},
|
| 221 |
+
author={Junbo Niu and Zheng Liu and Zhuangcheng Gu and Bin Wang and Linke Ouyang and Zhiyuan Zhao and Tao Chu and Tianyao He and Fan Wu and Qintong Zhang and Zhenjiang Jin and others},
|
| 222 |
+
year={2025},
|
| 223 |
+
eprint={2509.22186},
|
| 224 |
+
archivePrefix={arXiv},
|
| 225 |
+
primaryClass={cs.CV},
|
| 226 |
+
url={https://arxiv.org/abs/2509.22186},
|
| 227 |
+
}
|
| 228 |
+
```
|
added_tokens.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 151643,
|
| 3 |
+
"<|im_start|>": 151644,
|
| 4 |
+
"<|im_end|>": 151645,
|
| 5 |
+
"<|object_ref_start|>": 151646,
|
| 6 |
+
"<|object_ref_end|>": 151647,
|
| 7 |
+
"<|box_start|>": 151648,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|quad_start|>": 151650,
|
| 10 |
+
"<|quad_end|>": 151651,
|
| 11 |
+
"<|vision_start|>": 151652,
|
| 12 |
+
"<|vision_end|>": 151653,
|
| 13 |
+
"<|vision_pad|>": 151654,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|video_pad|>": 151656,
|
| 16 |
+
"<|ref_start|>": 151657,
|
| 17 |
+
"<|ref_end|>": 151658,
|
| 18 |
+
"<|md_start|>": 151659,
|
| 19 |
+
"<|md_end|>": 151660,
|
| 20 |
+
"<ched>": 151661,
|
| 21 |
+
"<ecel>": 151662,
|
| 22 |
+
"<fcel>": 151663,
|
| 23 |
+
"<lcel>": 151664,
|
| 24 |
+
"<ucel>": 151665,
|
| 25 |
+
"<xcel>": 151666,
|
| 26 |
+
"<nl>": 151667,
|
| 27 |
+
"<|rotate_up|>": 151668,
|
| 28 |
+
"<|rotate_down|>": 151669,
|
| 29 |
+
"<|rotate_left|>": 151670,
|
| 30 |
+
"<|rotate_right|>": 151671,
|
| 31 |
+
"<|txt_contd|>": 151672,
|
| 32 |
+
"<|paratext|>": 151673
|
| 33 |
+
}
|
chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"vision_start_token_id": 151652,
|
| 9 |
+
"vision_end_token_id": 151653,
|
| 10 |
+
"vision_token_id": 151654,
|
| 11 |
+
"image_token_id": 151655,
|
| 12 |
+
"video_token_id": 151656,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 896,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 4864,
|
| 17 |
+
"max_position_embeddings": 16384,
|
| 18 |
+
"max_window_layers": 24,
|
| 19 |
+
"model_type": "qwen2_vl",
|
| 20 |
+
"num_attention_heads": 14,
|
| 21 |
+
"num_hidden_layers": 24,
|
| 22 |
+
"num_key_value_heads": 2,
|
| 23 |
+
"rms_norm_eps": 1e-06,
|
| 24 |
+
"rope_theta": 1000000.0,
|
| 25 |
+
"sliding_window": 16384,
|
| 26 |
+
"tie_word_embeddings": true,
|
| 27 |
+
"torch_dtype": "bfloat16",
|
| 28 |
+
"transformers_version": "4.41.2",
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"use_sliding_window": false,
|
| 31 |
+
"vision_config": {
|
| 32 |
+
"depth": 32,
|
| 33 |
+
"embed_dim": 1280,
|
| 34 |
+
"mlp_ratio": 4,
|
| 35 |
+
"num_heads": 16,
|
| 36 |
+
"in_chans": 3,
|
| 37 |
+
"hidden_size": 896,
|
| 38 |
+
"patch_size": 14,
|
| 39 |
+
"spatial_merge_size": 2,
|
| 40 |
+
"spatial_patch_size": 14,
|
| 41 |
+
"temporal_patch_size": 2
|
| 42 |
+
},
|
| 43 |
+
"rope_scaling": {
|
| 44 |
+
"type": "mrope",
|
| 45 |
+
"mrope_section": [
|
| 46 |
+
8,
|
| 47 |
+
12,
|
| 48 |
+
12
|
| 49 |
+
]
|
| 50 |
+
},
|
| 51 |
+
"vocab_size": 151936
|
| 52 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"pad_token_id": 151643,
|
| 4 |
+
"do_sample": true,
|
| 5 |
+
"eos_token_id": [
|
| 6 |
+
151645,
|
| 7 |
+
151643
|
| 8 |
+
],
|
| 9 |
+
"repetition_penalty": 1.0,
|
| 10 |
+
"temperature": 0.01,
|
| 11 |
+
"top_p": 0.001,
|
| 12 |
+
"top_k": 1,
|
| 13 |
+
"transformers_version": "4.37.0"
|
| 14 |
+
}
|
| 15 |
+
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41256db636a3e619a55f4349e21c0403f27c91fd1b03655359c3092497cecd89
|
| 3 |
+
size 2312126640
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"min_pixels": 3136,
|
| 3 |
+
"max_pixels": 1605632,
|
| 4 |
+
"patch_size": 14,
|
| 5 |
+
"temporal_patch_size": 2,
|
| 6 |
+
"merge_size": 2,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.48145466,
|
| 9 |
+
0.4578275,
|
| 10 |
+
0.40821073
|
| 11 |
+
],
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 18 |
+
"processor_class": "Qwen2VLProcessor"
|
| 19 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,228 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<|im_start|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "<|im_end|>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"content": "<|object_ref_start|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"content": "<|object_ref_end|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"content": "<|box_start|>",
|
| 33 |
+
"lstrip": false,
|
| 34 |
+
"normalized": false,
|
| 35 |
+
"rstrip": false,
|
| 36 |
+
"single_word": false
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"content": "<|box_end|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"content": "<|quad_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"content": "<|quad_end|>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"content": "<|vision_start|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"content": "<|vision_end|>",
|
| 68 |
+
"lstrip": false,
|
| 69 |
+
"normalized": false,
|
| 70 |
+
"rstrip": false,
|
| 71 |
+
"single_word": false
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"content": "<|vision_pad|>",
|
| 75 |
+
"lstrip": false,
|
| 76 |
+
"normalized": false,
|
| 77 |
+
"rstrip": false,
|
| 78 |
+
"single_word": false
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"content": "<|image_pad|>",
|
| 82 |
+
"lstrip": false,
|
| 83 |
+
"normalized": false,
|
| 84 |
+
"rstrip": false,
|
| 85 |
+
"single_word": false
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"content": "<|video_pad|>",
|
| 89 |
+
"lstrip": false,
|
| 90 |
+
"normalized": false,
|
| 91 |
+
"rstrip": false,
|
| 92 |
+
"single_word": false
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"content": "<|ref_start|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"content": "<|ref_end|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"content": "<|md_start|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"content": "<|md_end|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"content": "<ched>",
|
| 124 |
+
"lstrip": false,
|
| 125 |
+
"normalized": false,
|
| 126 |
+
"rstrip": false,
|
| 127 |
+
"single_word": false
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"content": "<ecel>",
|
| 131 |
+
"lstrip": false,
|
| 132 |
+
"normalized": false,
|
| 133 |
+
"rstrip": false,
|
| 134 |
+
"single_word": false
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"content": "<fcel>",
|
| 138 |
+
"lstrip": false,
|
| 139 |
+
"normalized": false,
|
| 140 |
+
"rstrip": false,
|
| 141 |
+
"single_word": false
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"content": "<lcel>",
|
| 145 |
+
"lstrip": false,
|
| 146 |
+
"normalized": false,
|
| 147 |
+
"rstrip": false,
|
| 148 |
+
"single_word": false
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"content": "<ucel>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"content": "<xcel>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"content": "<nl>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"content": "<|rotate_up|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"content": "<|rotate_down|>",
|
| 180 |
+
"lstrip": false,
|
| 181 |
+
"normalized": false,
|
| 182 |
+
"rstrip": false,
|
| 183 |
+
"single_word": false
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"content": "<|rotate_left|>",
|
| 187 |
+
"lstrip": false,
|
| 188 |
+
"normalized": false,
|
| 189 |
+
"rstrip": false,
|
| 190 |
+
"single_word": false
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"content": "<|rotate_right|>",
|
| 194 |
+
"lstrip": false,
|
| 195 |
+
"normalized": false,
|
| 196 |
+
"rstrip": false,
|
| 197 |
+
"single_word": false
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"content": "<|txt_contd|>",
|
| 201 |
+
"lstrip": false,
|
| 202 |
+
"normalized": false,
|
| 203 |
+
"rstrip": false,
|
| 204 |
+
"single_word": false
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"content": "<|paratext|>",
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"normalized": false,
|
| 210 |
+
"rstrip": false,
|
| 211 |
+
"single_word": false
|
| 212 |
+
}
|
| 213 |
+
],
|
| 214 |
+
"eos_token": {
|
| 215 |
+
"content": "<|im_end|>",
|
| 216 |
+
"lstrip": false,
|
| 217 |
+
"normalized": false,
|
| 218 |
+
"rstrip": false,
|
| 219 |
+
"single_word": false
|
| 220 |
+
},
|
| 221 |
+
"pad_token": {
|
| 222 |
+
"content": "<|endoftext|>",
|
| 223 |
+
"lstrip": false,
|
| 224 |
+
"normalized": false,
|
| 225 |
+
"rstrip": false,
|
| 226 |
+
"single_word": false
|
| 227 |
+
}
|
| 228 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,296 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"151643": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"151644": {
|
| 13 |
+
"content": "<|im_start|>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"151645": {
|
| 21 |
+
"content": "<|im_end|>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"151646": {
|
| 29 |
+
"content": "<|object_ref_start|>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"151647": {
|
| 37 |
+
"content": "<|object_ref_end|>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"151648": {
|
| 45 |
+
"content": "<|box_start|>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"151649": {
|
| 53 |
+
"content": "<|box_end|>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"151650": {
|
| 61 |
+
"content": "<|quad_start|>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"151651": {
|
| 69 |
+
"content": "<|quad_end|>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"151652": {
|
| 77 |
+
"content": "<|vision_start|>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"151653": {
|
| 85 |
+
"content": "<|vision_end|>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"151654": {
|
| 93 |
+
"content": "<|vision_pad|>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"151655": {
|
| 101 |
+
"content": "<|image_pad|>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"151656": {
|
| 109 |
+
"content": "<|video_pad|>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"151657": {
|
| 117 |
+
"content": "<|ref_start|>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"151658": {
|
| 125 |
+
"content": "<|ref_end|>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"151659": {
|
| 133 |
+
"content": "<|md_start|>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"151660": {
|
| 141 |
+
"content": "<|md_end|>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"151661": {
|
| 149 |
+
"content": "<ched>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"151662": {
|
| 157 |
+
"content": "<ecel>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"151663": {
|
| 165 |
+
"content": "<fcel>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"151664": {
|
| 173 |
+
"content": "<lcel>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"151665": {
|
| 181 |
+
"content": "<ucel>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"151666": {
|
| 189 |
+
"content": "<xcel>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
+
},
|
| 196 |
+
"151667": {
|
| 197 |
+
"content": "<nl>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
"151668": {
|
| 205 |
+
"content": "<|rotate_up|>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
+
},
|
| 212 |
+
"151669": {
|
| 213 |
+
"content": "<|rotate_down|>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"151670": {
|
| 221 |
+
"content": "<|rotate_left|>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"151671": {
|
| 229 |
+
"content": "<|rotate_right|>",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"151672": {
|
| 237 |
+
"content": "<|txt_contd|>",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"151673": {
|
| 245 |
+
"content": "<|paratext|>",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
}
|
| 252 |
+
},
|
| 253 |
+
"additional_special_tokens": [
|
| 254 |
+
"<|im_start|>",
|
| 255 |
+
"<|im_end|>",
|
| 256 |
+
"<|object_ref_start|>",
|
| 257 |
+
"<|object_ref_end|>",
|
| 258 |
+
"<|box_start|>",
|
| 259 |
+
"<|box_end|>",
|
| 260 |
+
"<|quad_start|>",
|
| 261 |
+
"<|quad_end|>",
|
| 262 |
+
"<|vision_start|>",
|
| 263 |
+
"<|vision_end|>",
|
| 264 |
+
"<|vision_pad|>",
|
| 265 |
+
"<|image_pad|>",
|
| 266 |
+
"<|video_pad|>",
|
| 267 |
+
"<|ref_start|>",
|
| 268 |
+
"<|ref_end|>",
|
| 269 |
+
"<|md_start|>",
|
| 270 |
+
"<|md_end|>",
|
| 271 |
+
"<ched>",
|
| 272 |
+
"<ecel>",
|
| 273 |
+
"<fcel>",
|
| 274 |
+
"<lcel>",
|
| 275 |
+
"<ucel>",
|
| 276 |
+
"<xcel>",
|
| 277 |
+
"<nl>",
|
| 278 |
+
"<|rotate_up|>",
|
| 279 |
+
"<|rotate_down|>",
|
| 280 |
+
"<|rotate_left|>",
|
| 281 |
+
"<|rotate_right|>",
|
| 282 |
+
"<|txt_contd|>",
|
| 283 |
+
"<|paratext|>"
|
| 284 |
+
],
|
| 285 |
+
"bos_token": null,
|
| 286 |
+
"chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
| 287 |
+
"clean_up_tokenization_spaces": false,
|
| 288 |
+
"eos_token": "<|im_end|>",
|
| 289 |
+
"padding_side": "left",
|
| 290 |
+
"errors": "replace",
|
| 291 |
+
"model_max_length": 16384,
|
| 292 |
+
"pad_token": "<|endoftext|>",
|
| 293 |
+
"split_special_tokens": false,
|
| 294 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 295 |
+
"unk_token": null
|
| 296 |
+
}
|
video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"min_pixels": 3136,
|
| 3 |
+
"max_pixels": 1605632,
|
| 4 |
+
"patch_size": 14,
|
| 5 |
+
"temporal_patch_size": 2,
|
| 6 |
+
"merge_size": 2,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.48145466,
|
| 9 |
+
0.4578275,
|
| 10 |
+
0.40821073
|
| 11 |
+
],
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 18 |
+
"processor_class": "Qwen2VLProcessor"
|
| 19 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|