Transformers
llamafile
mixtral
jartine commited on
Commit
a3f90ca
1 Parent(s): 5011535

Quantize mixtral-8x7b-instruct-v0.1 with llamafile-0.8 Q4_K_M

Browse files
mixtral-8x7b-instruct-v0.1.Q4_K_M.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d4737e32032af170735dee6d528062da6b1f1535d08e72d3249793276b3f413
3
- size 28472775159
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e7c9def5f7644c1eca4a5183af42d492b05d7b46bb60d8e225a4b321fe60b3f
3
+ size 28475593453