jartine commited on
Commit
2b1e56f
·
verified ·
1 Parent(s): 34763ef

Quantize Q8_0 with llamafile-0.9.0

Browse files
Mistral-7B-Instruct-v0.3.Q8_0.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e7ab9bcbe2bda5849cf5fc0139423900444c38e073dfc5c449cff1835d34f87
3
- size 7732345098
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a76fe6e11167327c85d29c43f0783211e9f34966f0705d1324f3f9bde143585
3
+ size 7945408820