Instructions to use deepseek-community/DeepSeek-OCR-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deepseek-community/DeepSeek-OCR-2 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="deepseek-community/DeepSeek-OCR-2")

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

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

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use deepseek-community/DeepSeek-OCR-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deepseek-community/DeepSeek-OCR-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-community/DeepSeek-OCR-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/deepseek-community/DeepSeek-OCR-2

SGLang

How to use deepseek-community/DeepSeek-OCR-2 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "deepseek-community/DeepSeek-OCR-2" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-community/DeepSeek-OCR-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "deepseek-community/DeepSeek-OCR-2" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "deepseek-community/DeepSeek-OCR-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use deepseek-community/DeepSeek-OCR-2 with Docker Model Runner:
```
docker model run hf.co/deepseek-community/DeepSeek-OCR-2
```

🌟 Github | 📥 Original Model | 📄 Paper | 📄 Arxiv

DeepSeek-OCR 2: Visual Causal Flow

Explore more human-like visual encoding.

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="<image>\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 <|grounding|> token enables coordinate-aware output with <|ref|> and <|det|> tags.

inputs = processor(
    images=image,
    text="<image>\n<|grounding|>Convert 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))
# "<|ref|>title<|/ref|><|det|>[[330, 198, 558, 230]]<|/det|>\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:        "<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

@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}
}

Downloads last month: 173

Safetensors

Model size

3B params

Tensor type

BF16

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Papers for deepseek-community/DeepSeek-OCR-2

DeepSeek-OCR 2: Visual Causal Flow

Paper • 2601.20552 • Published Jan 28 • 70

DeepSeek-OCR: Contexts Optical Compression

Paper • 2510.18234 • Published Oct 21, 2025 • 94