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
```

The model inference seems to be broken

by sovitrath - opened Feb 8

Discussion

sovitrath

Feb 8

Getting weird outputs in both grounding and free ocr model for even simple documents which are working fine directly via Hugging Face.
I was going to fine-tune but don't want to fine-tune over a broken pipeline at the moment.
Uploading the image I tested among many along wih the output in the free ocr mode. Anyone else facing similar issue?

TRADER JOE’S
2001 Greenville Ave
Dallas TX 75206
Store #403 - (469) 334-0614

OPEN 8:00AM TO 9:00PM DAILY

R-CARROTS SHREDDED 10 OZ
R-CUCUMBERS PERSIAN 1 LB
BANANAS 4 1/2 LB
TOMATOES CRUSHED NO SALT
ORGANIC WHOLE NO SALT
MINI-PEARL TOMATOES
1.29
1.99
2.49
0.87
0.99
0.99
0.99
0.99
0.99
0.98
0.99
0.99
0.99
0.99
0.89
0.99
0.99
0.99
0.99
0.68
0.68
0.68

The text output goes on like this.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment