Transformers
llamafile
mixtral
jartine commited on
Commit
90b10c0
1 Parent(s): 96782d0

Quantize mixtral-8x7b-instruct-v0.1 with llamafile-0.7 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:b12083dc28ec199e74f74686b4102d81ee2458b494f2bec5fb090a2235adad5e
3
- size 26475368846
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d4737e32032af170735dee6d528062da6b1f1535d08e72d3249793276b3f413
3
+ size 28472775159