jartine commited on
Commit
6bfdff5
1 Parent(s): 682f2fa

Quantize Q4_K_M with llamafile-0.8.7

Browse files
Mistral-7B-Instruct-v0.3.Q4_K_M.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a82160a60ec4a75b85c5f01cec244520d35f4529842c7e4db306a62b8a26633a
3
- size 4408359087
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9c0346dfc602f2f753bd90efcc8cc74529633649bbeca410bad289dd6990c17
3
+ size 4398528688