Image-Text-to-Text
Transformers
Safetensors
multilingual
deepseek_vl_v2
feature-extraction
deepseek
vision-language
ocr
custom_code
Eval Results
Instructions to use deepseek-ai/DeepSeek-OCR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use deepseek-ai/DeepSeek-OCR with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="deepseek-ai/DeepSeek-OCR", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("deepseek-ai/DeepSeek-OCR", trust_remote_code=True, device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use deepseek-ai/DeepSeek-OCR with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "deepseek-ai/DeepSeek-OCR" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "deepseek-ai/DeepSeek-OCR", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/deepseek-ai/DeepSeek-OCR
- SGLang
How to use deepseek-ai/DeepSeek-OCR 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-ai/DeepSeek-OCR" \ --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-ai/DeepSeek-OCR", "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-ai/DeepSeek-OCR" \ --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-ai/DeepSeek-OCR", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use deepseek-ai/DeepSeek-OCR with Docker Model Runner:
docker model run hf.co/deepseek-ai/DeepSeek-OCR
Can I extract the information from the invoice in JSON form using the DeepSeek OCR model?
#103
by zabih1 - opened
I want to extract invoice fields in the JSON form. Can I use this model?
Yes, you can. You need to prompt the DeepSeek OCR model with the JSON schema that you want to extract from the image. Or else if your JSON schema is complex, try to extract the markdown text using deepseek ocr and use any small LLM model to convert the markdown data into JSON output.
If you want direct JSON output and with the best accuracy, I would suggest to go with mistral ocr 3 model.