jartine commited on
Commit
b540506
·
verified ·
1 Parent(s): 29a5edc

Quantize Q6_K with llamafile-0.8.7

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 sha256:93837c1b57739d3b43aab4883bc6dc34c704116f01f8198119aa51cc090c4f71
3
- size 5982795947
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:749cfaf43512bbea8d13a4c08445c12720c95fa4e14fdd4f51e325a524e04f9b
3
+ size 5972965548