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

Libraries

How to use unsloth/DeepSeek-OCR-2 with Transformers:

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

pipe = pipeline("image-text-to-text", model="unsloth/DeepSeek-OCR-2", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("unsloth/DeepSeek-OCR-2", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use unsloth/DeepSeek-OCR-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/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": "unsloth/DeepSeek-OCR-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/unsloth/DeepSeek-OCR-2

SGLang

How to use unsloth/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 "unsloth/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": "unsloth/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 "unsloth/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": "unsloth/DeepSeek-OCR-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use unsloth/DeepSeek-OCR-2 with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/DeepSeek-OCR-2 to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/DeepSeek-OCR-2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/DeepSeek-OCR-2 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="unsloth/DeepSeek-OCR-2",
    max_seq_length=2048,
)

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

Read our Guide How to: Run & Fine-tune DeepSeek-OCR 2.

This DeepSeek-OCR 2 upload was edited to enable inference & fine-tuning on the latest transformers (no accuracy change).

✨ Read our DeepSeek-OCR 2 Guide here!

Fine-tune DeepSeek-OCR 2 for free using our Google Colab notebook
View the rest of our notebooks in our docs here.

🌟 Github | 📥 Model Download | 📄 Paper Link | 📄 Arxiv Paper Link |

DeepSeek-OCR 2: Visual Causal Flow

Explore more human-like visual encoding.

Usage

Inference using Huggingface transformers on NVIDIA GPUs. Requirements tested on python 3.12.9 + CUDA11.8：

torch==2.6.0
transformers==4.46.3
tokenizers==0.20.3
einops
addict 
easydict
pip install flash-attn==2.7.3 --no-build-isolation

from 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

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

Support-Modes

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

Prompts examples

# document: <image>\n<|grounding|>Convert the document to markdown.
# other image: <image>\n<|grounding|>OCR this image.
# without layouts: <image>\nFree OCR.
# figures in document: <image>\nParse the figure.
# general: <image>\nDescribe this image in detail.
# rec: <image>\nLocate <|ref|>xxxx<|/ref|> in the image.

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

coming soon~

Downloads last month: 110,730

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

Model tree for unsloth/DeepSeek-OCR-2

Base model

deepseek-ai/DeepSeek-OCR-2

Finetuned

(31)

this model

Adapters

5 models