LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding
Paper • 2306.17107 • Published • 12
NOTE: This "delta model" cannot be used directly. It should be merged with the LLaMA-13B checkpoint.
For more information, please refer to LLaVAR project page, Github repo, and paper.
- Downloads last month
- 16
Install from pip and serve model
# Install vLLM from pip: pip install vllm# Start the vLLM server: vllm serve "SALT-NLP/LLaVAR_delta"# Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "SALT-NLP/LLaVAR_delta", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'