4 bits quantization of LLMs using GPTQ
Why do you think that https://github.com/AlpinDale/pygmalion.cpp is a good alternative to GPTQ-for-LLaMa
4 bits quantization of LLMs using GPTQ
Why do you think that https://github.com/AlpinDale/pygmalion.cpp is a good alternative to GPTQ-for-LLaMa