lm-sys/FastChat

support for 4bit quantization from transfomer library.

Aperta

#1798 aperta il 27 giu 2023

 (7 commenti) (2 reazioni) (0 assegnatari)Python (4736 fork)batch import
enhancementgood first issue

Metriche repository

Star
 (38.959 stelle)
Metriche merge PR
 (Metriche PR in attesa)

Descrizione

Loading a vicuna13B using 4bit quantization from the transformers library is possible load_in_4bit. How difficult could be for Fastach to support it?

Guida contributor