Quantized version of this: https://huggingface.co/ausboss/llama-30b-supercot
GPTQ quantization using https://github.com/0cc4m/GPTQ-for-LLaMa for compatibility with 0cc4m's fork of KoboldAI
Command used to quantize:python llama.py c:\llama-30b-supercot c4 --wbits 4 --true-sequential --groupsize 128 --save_safetensors 4bit-128g.safetensors
Evaluation & Score (Lower is better):
- WikiText2: 4.51
- PTB: 17.46
- C4: 6.37
Non-groupsize version is here: https://huggingface.co/tsumeone/llama-30b-supercot-4bit-cuda