DeepSeek OCR

📥 Model Download | 📄 Paper Link | 📄 Arxiv Paper Link | Explore the boundaries of visual-text compression. Release [2025/x/x]🚀🚀🚀 We release DeepSeek-OCR, a model to investigate the role of vision encoders from an LLM-centric viewpoint. Contents Install Our environment is cuda11.8+torch2.6.0. Clone this repository and navigate to the DeepSeek-OCR folder git clone https://github.com/deepseek-ai/DeepSeek-OCR.git Conda conda create -n deepseek-ocr python=3.12.9 -y conda activate deepseek-ocr Packages download the vllm-0.8.5 whl pip install torch==2.6.0 torchvision==0.21.0 torchaudio==2.6.0 --index-url https://download.pytorch.org/whl/cu118 pip install vllm-0.8.5+cu118-cp38-abi3-manylinux1_x86_64.whl pip install -r requirements.txt pip install flash-attn==2.7.3 --no-build-isolation Note: if you want vLLM and transformers codes to run in the same environment, you don't need to worry about this installation error like: vllm 0.8.5+cu118 requires transformers>=4.51.1 VLLM: Note: change the INPUT_PATH/OUTPUT_PATH and other settings in the DeepSeek-OCR-master/DeepSeek-OCR-vllm/config.py cd DeepSeek-OCR-master/DeepSeek-OCR-vllm image: streaming output python run_dpsk_ocr_image.py pdf: concurrency ~2500tokens/s(an A100-40G) python run_dpsk_ocr_pdf.py batch eval for benchmarks python run_dpsk_ocr_eval_batch.py Transformers from transformers import AutoModel , AutoTokenizer import torch import os os . environ [ "CUDA_VISIBLE_DEVICES" ] = '0' model_name = 'deepseek-ai/DeepSeek-OCR' 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 = " Free OCR. " prompt = " <|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 = 640 , crop_mode = True , save_results = True , test_compress = True ) or you can cd DeepSeek-OCR-master/DeepSeek-OCR-hf python run_dpsk_ocr.py The current open-source model supports the following modes: Native resolution: Tiny: 512×512 （64 vision tokens）✅ Small: 640×640 （100 vision tokens）✅ Base: 1024×1024 （256 vision tokens）✅ Large: 1280×1280 （400 vision tokens）✅ Dynamic resolution Gundam: n×640×640 + 1×1024×1024 ✅ Prompts examples # document: <|grounding|>Convert the document to markdown. # other image: <|grounding|>OCR this image. # without layouts: Free OCR. # figures in document: Parse the figure. # general: Describe this image in detail. # rec: Locate <|ref|>xxxx<|/ref|> in the image. # '先天下之忧而忧' Visualizations Acknowledgement We would like to thank Vary, GOT-OCR2.0, MinerU, PaddleOCR, OneChart, Slow Perception for their valuable models and ideas. We also appreciate the benchmarks: Fox, OminiDocBench. Citation coming soon！