ODIN-RM & RLHF models
Collection
The ODIN and the policies trained by ODIN • 8 items • Updated
The model trained with L=1 (Length loss weight) and O=1 (Orthogonal loss weight).
- Downloads last month
- 11
The model trained with L=1 (Length loss weight) and O=1 (Orthogonal loss weight).
Install from pip and serve model
# Install vLLM from pip: pip install vllm# Start the vLLM server: vllm serve "Lichang-Chen/ODIN_L1_O1"# Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Lichang-Chen/ODIN_L1_O1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'