Transformers
llamafile
mixtral
jartine commited on
Commit
8e1afb3
1 Parent(s): ad02117

Quantize mixtral-8x7b-instruct-v0.1 with llamafile-0.8 Q5_K_M

Browse files
mixtral-8x7b-instruct-v0.1.Q5_K_M.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:afa0d5a58cbc3674196008b0ff03a423cc10aa190fc8c9d36f162b27dcb1d257
3
- size 33253954034
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31d01eca215becf08de8b5091f92aee5da9c8f8dbb1089eef509bffe560fc3f0
3
+ size 33256706797