🌟 Github | 📥 模型下载 | 📄 论文链接 | 📄 Arxiv 论文链接 |
使用方法
在 NVIDIA GPU 上使用 Huggingface transformers 进行推理。已在 python 3.12.9 + CUDA11.8 环境下测试通过：
torch==2.6.0
transformers==4.46.3
tokenizers==0.20.3
einops
addict
easydict
pip install flash-attn==2.7.3 --no-build-isolationfrom 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
有关模型推理加速和PDF处理等方面的指导，请参考🌟GitHub。
支持模式
- 动态分辨率
- 默认：(0-6)×768×768 + 1×1024×1024 — (0-6)×144 + 256 视觉 tokens ✅
主要提示词
# document: <image>\n<|grounding|>Convert the document to markdown.
# without layouts: <image>\nFree OCR.致谢
感谢 DeepSeek-OCR、Vary、GOT-OCR2.0、MinerU、PaddleOCR 提供的宝贵模型和思想。
同时，感谢基准测试 OmniDocBench。
引用
@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}
}