jartine commited on
Commit
8d06b20
·
verified ·
1 Parent(s): f7317e9

Quantize Q2_K with llamafile-0.9.0

Browse files
Mistral-7B-Instruct-v0.3.Q2_K.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:966de5c3e7f73c982a5e09b83bd28cf79f38bf642426ab63f4f9543507585e7d
3
- size 2752657674
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbcf6d2562d648e92de2bc3a6b1a98c5a386e4aa7a156e9eb375b1cb8d8506b8
3
+ size 2965721396