Transformers
llamafile
mixtral
jartine commited on
Commit
ad02117
1 Parent(s): 9839b2c

Quantize mixtral-8x7b-instruct-v0.1 with llamafile-0.7.3 Q4_1

Browse files
mixtral-8x7b-instruct-v0.1.Q4_1.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcf97336edb21db56478770c4554e7c015846647de1e007909a2216aa93977e1
3
- size 29361770995
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8ac85674a453e1efb1af45ea9dc5f547d8b09b58a8192b39a4e0d6ab10d593f
3
+ size 29361836526