Transformers
llamafile
mixtral
jartine commited on
Commit
cc2c274
1 Parent(s): 9e28dfa

Quantize Q3_K_M with llamafile-0.8.12

Browse files
mixtral-8x7b-instruct-v0.1.Q3_K_M.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64b4cd5da54428dca108992d17dd1f27116e2c7db6a4d2dc03bb1bbe9ceadbe4
3
- size 22576511165
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e2788006a3684cfbe40d0b2d68a6699f3b74a91e784c2c9f95ac3202d86b2be
3
+ size 22576380093