# deepseek-ocr2

**Repository Path**: alan-ding/deepseek-ocr2

## Basic Information

- **Project Name**: deepseek-ocr2
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 1
- **Forks**: 0
- **Created**: 2026-01-29
- **Last Updated**: 2026-04-10

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

## model
https://www.modelscope.cn/models/deepseek-ai/DeepSeek-OCR-2

## install refer to v1 usage section
https://gitee.com/hf-models/DeepSeek-OCR

## start
```
1. git clone https://gitee.com/alan-ding/deepseek-ocr2.git

2. pip install -r global-requirements.txt

3. uv venv

4. set 'pyvenv.cfg' for include-system-site-packages = true in .venv

5. active venv

6. uv sync

7. delete 'torch', 'torchvision' in .venv

8. python infer.py
```

## download model
```
modelscope download --model deepseek-ai/DeepSeek-OCR-2 --local_dir ./model
```

## test
![alt text](image.png)

![alt text](image-3.png)

![alt text](image-2.png)