tsumeone/

llama-30b-supercot-4bit-128g-cuda

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):

Non-groupsize version is here: https://huggingface.co/tsumeone/llama-30b-supercot-4bit-cuda