jartine commited on
Commit
f0d9334
·
verified ·
1 Parent(s): d01cde8

Quantize Q6_K with llamafile-0.9.0

Browse files
Mistral-7B-Instruct-v0.3.Q6_K.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71c5af0874e71435e105e5d3d66ea58b092db800aa0854be2bd59ae008b1f4d2
3
- size 5977028874
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9b7bac7f819029e8605a71ae77494f93867e83b1fc5df05c553cb21b0717035
3
+ size 6190092596