search

OpenGVLab / OmniQuant

[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.
MIT License
689 stars 53 forks source link

[fix] attention_mask may appear None for newer versions of LLaMA #47

Closed xingchensong closed 9 months ago

xingchensong commented 9 months ago

fix https://github.com/OpenGVLab/OmniQuant/issues/46

ChenMnZ commented 9 months ago

Thanks for your time for this PR.