| pip install --upgrade huggingface_hub git+https://github.com/vllm-project/llm-compressor.git@038ea3cf424b65fb3afa49743d1c37bb572a0244 | |
| apt-get update | |
| apt-get install nano -y | |
| huggingface-cli download ArliAI/Llama-3.1-70B-ArliAI-RPMax-v1.3 --max-workers 16 | |
| python compress.py | |