Transformers
llamafile
mixtral
jartine commited on
Commit
9e28dfa
1 Parent(s): 53eaecc

Quantize Q3_K_S with llamafile-0.8.12

Browse files
mixtral-8x7b-instruct-v0.1.Q3_K_S.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0259217ee8c3b558085a7087011a6b3b5a45af4bfac810150ab87685f2790e91
3
- size 20462581949
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ae2dbd6321caf35329d81c0c6059fc3eeeae68354d2932b59b5830901e0e11d
3
+ size 20462450877