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 Settings

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

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
```

danielhanchen commited on about 1 month ago

Commit

4268fcf

verified ·

1 Parent(s): 7b55650

Fix UnboundLocalError for unsupported base_size in vision encoder

Browse files

Files changed (1) hide show

deepencoderv2.py +5 -0

deepencoderv2.py CHANGED Viewed

@@ -441,6 +441,11 @@ class Qwen2Decoder2Encoder(nn.Module):
             param_img = self.query_768.weight
         elif n_query == 256:
             param_img = self.query_1024.weight
         batch_query_imgs = param_img.unsqueeze(0).expand(
             bs, -1, -1

             param_img = self.query_768.weight
         elif n_query == 256:
             param_img = self.query_1024.weight
+        else:
+            raise ValueError(
+                f"Unsupported base_size: vision encoder expects 768 or 1024 "
+                f"(got {n_query} queries, need 144 or 256)."
+            )
         batch_query_imgs = param_img.unsqueeze(0).expand(
             bs, -1, -1