Can i quantize HF version of llama model - Githubissues

qwopqwop200 / GPTQ-for-LLaMa

4 bits quantization of LLaMA using GPTQ

Apache License 2.0

2.99k stars 459 forks source link

Can i quantize HF version of llama model #279

Open akanyaani opened 1 year ago