lm-sys/FastChat

support for 4bit quantization from transfomer library.

Offen

#1.798 geöffnet am 27.06.2023

 (7 Kommentare) (2 Reaktionen) (0 zugewiesene Personen)Python (4.736 Forks)batch import
enhancementgood first issue

Repository-Metriken

Stars
 (38.959 Sterne)
PR-Merge-Metriken
 (PR-Metriken ausstehend)

Beschreibung

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

Contributor Guide