search

qwopqwop200 / GPTQ-for-LLaMa

4 bits quantization of LLaMA using GPTQ
Apache License 2.0
2.98k stars 457 forks source link

Does this work for gptj specifically the cuda branch? Thanks! #250

Open ArEnSc opened 1 year ago

ArEnSc commented 1 year ago

Hey looking through most of the issues and code don't see references of gpt-j wondering if this supports pyg 6B