jartine commited on
Commit
169f8e0
1 Parent(s): b0d2666

Quantize Q8_0 with llamafile-0.8.5

Browse files
Meta-Llama-3-8B-Instruct.Q8_0.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:406868a97f02f57183716c7e4441d427f223fdbc7fa42964ef10c4d60dd8ed37
3
- size 8570222974
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d03233ccb38e7c0c297519e223c1e9a08382d053afba2286e67088567ae8a9d4
3
+ size 8576383279