Transformers
llamafile
mixtral
jartine commited on
Commit
b1df4c3
1 Parent(s): 812d4de

Quantize Q5_K_S with llamafile-0.8.12

Browse files
mixtral-8x7b-instruct-v0.1.Q5_K_S.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7dc0c8c833bc4f7afb51d489bde860fba30da5319994d585ba0ef39bb17f636c
3
- size 32261421245
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ba8754a1184c682d621de0cfea651f491e2211e9ca3dbad355d99ad181c32a9
3
+ size 32261290173