4-bit quantized files for XuYipei/kw-cutegpt-13b-ift

CuteGPT is an open-source conversational language model that supports both Chinese and English, developed by Fudan University KnowledgeWorks Laboratory.

Quantized using GPTQ-for-LLaMa.

Command used to quantize: python llama.py /my/model/directory c4 --wbits 4 --true-sequential --act-order --save_safetensors /my/output/file.safetensors