search

qwopqwop200 / GPTQ-for-LLaMa

4 bits quantization of LLaMA using GPTQ
Apache License 2.0
2.99k stars 459 forks source link

neox.py needs to add "import math" #282

Open StudyingShao opened 1 year ago

StudyingShao commented 1 year ago

https://github.com/qwopqwop200/GPTQ-for-LLaMa/blob/e985b700f19e670bad9b949cd83056889dd31448/neox.py#L302 This line needs "import math" on the head.