An alpaca fine-tune of chargoddard's Llamafied Yi-6B. This works fine, unlike the lobotomized Llama model I tried merging it with.
Uploaded model
- Developed by: reallad
- License: apache-2.0
- Finetuned from model : chargoddard/Yi-6B-Llama
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Downloads last month
- 15
Model tree for reallad/llamayialpaca
Base model
chargoddard/Yi-6B-Llama
Install from pip and serve model
# Install vLLM from pip: pip install vllm# Start the vLLM server: vllm serve "reallad/llamayialpaca"# Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "reallad/llamayialpaca", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'