Transformers
llamafile
mixtral
jartine commited on
Commit
36cda63
1 Parent(s): 5f8e853

Quantize mixtral-8x7b-instruct-v0.1 with llamafile-0.8.2 Q3_K_M

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 sha256:94863e9b814d5e993316e0fd026f129065229a196300701d143ad8c126d39afa
3
- size 22573552365
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20227fafef6a32d93265d7260a7e372bb89334d4cea04a48b07d5d1fe94d5a08
3
+ size 22575790261