├── .gitignore ├── README.md ├── cluster_friendly_linear.py ├── gpt2.py ├── quantizer.py ├── requirements.txt └── run.py /.gitignore: -------------------------------------------------------------------------------- 1 | env 2 | *.safetensors 3 | gpt2_4bit 4 | __pycache__ 5 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/smpanaro/apple-silicon-4bit-quant/HEAD/README.md -------------------------------------------------------------------------------- /cluster_friendly_linear.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/smpanaro/apple-silicon-4bit-quant/HEAD/cluster_friendly_linear.py -------------------------------------------------------------------------------- /gpt2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/smpanaro/apple-silicon-4bit-quant/HEAD/gpt2.py -------------------------------------------------------------------------------- /quantizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/smpanaro/apple-silicon-4bit-quant/HEAD/quantizer.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/smpanaro/apple-silicon-4bit-quant/HEAD/requirements.txt -------------------------------------------------------------------------------- /run.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/smpanaro/apple-silicon-4bit-quant/HEAD/run.py --------------------------------------------------------------------------------