This is a frankensteined Marx3b-v2 model (https://huggingface.co/acrastt/Marx-3B-V2)
It is approximately 7.1b. Just testing things out.
bfloat16
Used the same model 4 times. I fine-tuned it at r 256 but used the wrong alpaca format so I'll need to re-upload that merged model.
- Downloads last month
- 95
Install from pip and serve model
# Install vLLM from pip: pip install vllm# Start the vLLM server: vllm serve "ericpolewski/Marxish"# Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ericpolewski/Marxish", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'