DeepSeek-OCR-2

Usage

Plain OCR

from transformers import AutoProcessor, AutoModelForImageTextToText

model = AutoModelForImageTextToText.from_pretrained(
    "deepseek-community/DeepSeek-OCR-2", device_map="auto"
)
processor = AutoProcessor.from_pretrained("deepseek-community/DeepSeek-OCR-2")

image = "https://huggingface.co/datasets/hf-internal-testing/fixtures_got_ocr/resolve/main/image_ocr.jpg"
inputs = processor(images=image, text="\nFree OCR.", return_tensors="pt").to(model.device)

generate_ids = model.generate(**inputs, do_sample=False, max_new_tokens=256)
print(processor.decode(generate_ids[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))
# "R&D QUALITY IMPROVEMENT\nSUGGESTION/SOLUTION FORM\nName/Phone Ext. : (...)"

Grounding with markdown conversion

The token enables coordinate-aware output with and `` tags.

inputs = processor(
    images=image,
    text="\nConvert the document to markdown.",
    return_tensors="pt",
).to(model.device)

generate_ids = model.generate(**inputs, do_sample=False, max_new_tokens=256)
print(processor.decode(generate_ids[0, inputs["input_ids"].shape[1]:], skip_special_tokens=False))
# "title[[330, 198, 558, 230]]\n# R&D QUALITY (...)"

vLLM

Refer to 🌟GitHub for guidance on model inference acceleration and PDF processing.

Support-Modes

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

Main Prompts

# document:        "\nConvert the document to markdown."
# without layouts: "\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

@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}
}