text-generation-inference
Hotfix: fix of use of unquantized weights in Mixtral GQA loading
#2269
Merged
Merged
Hotfix: fix of use of unquantized weights in Mixtral GQA loading #2269
danieldk
merged
5 commits into
huggingface:main
from
main
Update idefics_causal_lm.py
0c7559b7
Merge branch 'huggingface:main' into main
28cecb66
fix dbrx & opt model prefix bug
39944e1c
Merge branch 'huggingface:main' into main
6111e9ec
Hotfix: fix of use of unquantized weights in Mixtral GQA loading
dc70cf9d
danieldk
approved these changes
on 2024-07-22
Login to write a write a comment.
Login via GitHub