Transformers
llamafile
mixtral
jartine commited on
Commit
28ed3f4
1 Parent(s): b321c10

Quantize mixtral-8x7b-instruct-v0.1 with llamafile-0.8.2 Q8_0

Browse files
mixtral-8x7b-instruct-v0.1.Q8_0.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38324f08d70171e93d3ccbf8a3cb5bc773c8fb5d7de3fd1ea7e4981ff6bc02e2
3
- size 49653420777
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1af668a50aa5e9fa277b4efffc1cac50db0e30b3bf40e90ebd7d7f99f5e1daf
3
+ size 49655658673