DeepSeek OCR 2

提供商deepseek-ai
分类ocr
许可证apache-2.0
下载量173.9K
星标81

简介

DeepSeek OCR 2 是一款专注于高精度文档数字化和图像文本识别的模型。与传统 OCR 仅能识别文字不同,它更强调对文档结构(如表格、公式、排版)的深度理解,能够将复杂的扫描件或图片直接转化为结构化的可编辑文本。对于开发者而言,它极大地降低了处理非结构化文档的预处理难度,非常适合用于自动化办公、知识库构建以及大规模文档数字化场景。其上手门槛较低,可作为 RAG 流程中关键的感知层,提升 LLM 对图片内容的理解质量。

核心亮点

  • 精准识别复杂表格与数学公式,还原文档结构
  • 极高文本还原度,有效降低后续 LLM 处理噪声
  • 适配 Apache-2.0 协议,企业级部署成本极低
  • 理想的 RAG 前置插件,提升多模态知识库质量

使用方法

安装依赖
# 安装 Hugging Face transformers
pip install transformers torch
SDK 使用
# 使用 transformers 加载模型
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("deepseek-ai/DeepSeek-OCR-2")
tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/DeepSeek-OCR-2")

Hugging Face 下载

我们推荐使用命令行或者 Hugging Face Hub SDK 来进行模型的下载。

操作指引:在下载前,请先通过如下命令安装 huggingface_hub:

操作指引
pip install -U huggingface_hub

命令行下载

下载完整模型库

下载完整模型库
huggingface-cli download deepseek-ai/DeepSeek-OCR-2

下载单个文件到指定本地文件夹(以下载 config.json 到当前路径下 ./dir 目录为例)

下载单个文件到指定本地文件夹(以下载 config.json 到当前路径下 ./dir 目录为例)
huggingface-cli download deepseek-ai/DeepSeek-OCR-2 config.json --local-dir ./dir

更多命令行下载选项,可参见官方文档

SDK 下载

SDK 下载
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('deepseek-ai/DeepSeek-OCR-2')

Git 下载

请确保 lfs 已经被正确安装

Git 下载
git lfs install
git clone https://huggingface.co/deepseek-ai/DeepSeek-OCR-2

如果您希望跳过 lfs 大文件下载,可以使用如下命令

跳过 LFS
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/deepseek-ai/DeepSeek-OCR-2

模型文件托管在 Hugging Face Hub,使用 HF CLI / SDK / Git 直接下载,不经过本站。

PyTorch / Transformers 使用

安装 Transformers

安装 Transformers
pip install -U transformers torch

模型加载和推理

模型加载和推理
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('deepseek-ai/DeepSeek-OCR-2')
tokenizer = AutoTokenizer.from_pretrained('deepseek-ai/DeepSeek-OCR-2')

模型下载

我们推荐使用命令行或者 ModelScope SDK 来进行模型的下载。

操作指引:在下载前,请先通过如下命令安装 ModelScope:

操作指引
pip install modelscope

命令行下载

下载完整模型库

下载完整模型库
modelscope download --model deepseek-ai/DeepSeek-OCR-2

下载单个文件到指定本地文件夹(以下载 README.md 到当前路径下 dir 目录为例)

下载单个文件到指定本地文件夹(以下载 README.md 到当前路径下 dir 目录为例)
modelscope download --model deepseek-ai/DeepSeek-OCR-2 README.md --local_dir ./dir

更多更丰富的命令行下载选项,可参见具体文档

SDK 下载

SDK 下载
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('deepseek-ai/DeepSeek-OCR-2')

Git 下载

请确保 lfs 已经被正确安装

Git 下载
git lfs install
git clone https://www.modelscope.cn/deepseek-ai/DeepSeek-OCR-2.git

如果您希望跳过 lfs 大文件下载,可以使用如下命令

跳过 LFS
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/deepseek-ai/DeepSeek-OCR-2.git

ModelScope 模型页直接下载模型文件;无需将模型文件放在本站服务器。

Notebook 快速开发

下载并安装 ModelScope library

下载并安装 ModelScope library
pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

模型加载和推理

模型加载和推理
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'deepseek-ai/DeepSeek-OCR-2')

完整文档

来源: HuggingFace

---
pipeline_tag: image-text-to-text
language:

  • multilingual

tags:
  • deepseek

  • vision-language

  • ocr

  • custom_code

license: apache-2.0
library_name: transformers
---
<div align="center">
<img src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/logo.svg?raw=true" width="60%" alt="DeepSeek AI" />
</div>
<hr>
<div align="center">
<a href="https://www.deepseek.com/" target="_blank">
<img alt="Homepage" src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/badge.svg?raw=true" />
</a>
<a href="https://huggingface.co/deepseek-ai/DeepSeek-OCR-2" target="_blank">
<img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-DeepSeek%20AI-ffc107?color=ffc107&logoColor=white" />
</a>

</div>

<div align="center">

<a href="https://discord.gg/Tc7c45Zzu5" target="_blank">
<img alt="Discord" src="https://img.shields.io/badge/Discord-DeepSeek%20AI-7289da?logo=discord&logoColor=white&color=7289da" />
</a>
<a href="https://twitter.com/deepseek_ai" target="_blank">
<img alt="Twitter Follow" src="https://img.shields.io/badge/Twitter-deepseek_ai-white?logo=x&logoColor=white" />
</a>

</div>

<p align="center">
<a href="https://github.com/deepseek-ai/DeepSeek-OCR-2"><b>🌟 Github</b></a> |
<a href="https://huggingface.co/deepseek-ai/DeepSeek-OCR-2"><b>📥 Model Download</b></a> |
<a href="https://github.com/deepseek-ai/DeepSeek-OCR-2/blob/main/DeepSeek_OCR2_paper.pdf"><b>📄 Paper Link</b></a> |
<a href="https://arxiv.org/abs/2601.20552"><b>📄 Arxiv Paper Link</b></a> |
</p>
<h2>
<p align="center">
<a href="">DeepSeek-OCR 2: Visual Causal Flow</a>
</p>
</h2>
<p align="center">
<img src="assets/fig1.png" style="width: 900px" align=center>
</p>
<p align="center">
<a href="">Explore more human-like visual encoding.</a>
</p>

Usage

Inference using Huggingface transformers on NVIDIA GPUs. Requirements tested on python 3.12.9 + CUDA11.8:

code
torch==2.6.0
transformers==4.46.3
tokenizers==0.20.3
einops
addict 
easydict
pip install flash-attn==2.7.3 --no-build-isolation
python
from transformers import AutoModel, AutoTokenizer
import torch
import os
os.environ["CUDA_VISIBLE_DEVICES"] = '0'
model_name = 'deepseek-ai/DeepSeek-OCR-2'

tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModel.from_pretrained(model_name, _attn_implementation='flash_attention_2', trust_remote_code=True, use_safetensors=True)
model = model.eval().cuda().to(torch.bfloat16)

prompt = "<image>\nFree OCR. "

prompt = "<image>\n<|grounding|>Convert the document to markdown. " image_file = 'your_image.jpg' output_path = 'your/output/dir'

res = model.infer(tokenizer, prompt=prompt, image_file=image_file, output_path = output_path, base_size = 1024, image_size = 768, crop_mode=True, save_results = True)

vLLM

Refer to 🌟GitHub for guidance on model inference acceleration and PDF processing, etc.<!-- -->

Support-Modes

  • Dynamic resolution
- Default: (0-6)×768×768 + 1×1024×1024 — (0-6)×144 + 256 visual tokens ✅

Main Prompts

python
# document: <image>\n<|grounding|>Convert the document to markdown.

without layouts: <image>\nFree OCR.

Acknowledgement

We would like to thank DeepSeek-OCR, Vary, GOT-OCR2.0, MinerU, PaddleOCR for their valuable models and ideas.

We also appreciate the benchmark OmniDocBench.

Citation

```bibtex
@article{wei2025deepseek,
title={DeepSeek-OCR: Contexts Optical Compression},
author={Wei, Haoran and Sun, Yaofeng and Li, Yukun},
journal={arXiv preprint arXiv:2510.18234},
year={2025}
}
@article{wei2026deepseek,
title={DeepSeek-OCR 2: Visual Causal Flow},
author={Wei, Haoran and Sun, Yaofeng and Li, Yukun},
journal={arXiv preprint arXiv:2601.20552},
year={2026}
}