jartine commited on
Commit
0ad2b69
1 Parent(s): bdbee7f

Quantize Q2_K with llamafile-0.8.9

Browse files
Meta-Llama-3-8B-Instruct.Q2_K.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6876ace66c5a350366301e1a3f1652e3fd28af36fe597e9c69ad52f11007c493
3
- size 3204921648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5c6822a4b706a9499d03e08177877dc788978294f276e00dd77db611ac0a569
3
+ size 3209312646