search

bitsandbytes-foundation / bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.
https://huggingface.co/docs/bitsandbytes/main/en/index
MIT License
6.31k stars 634 forks source link

fix 4bit dtype #1325

Closed jiqing-feng closed 3 months ago

jiqing-feng commented 3 months ago

Fix error check for model weight dtype.

jiqing-feng commented 3 months ago

Hi @Titus-von-Koeller , please merge this PR for 4bit saving bug.