jartine commited on
Commit
29f79ef
1 Parent(s): 2b167ff

Quantize Meta-Llama-3-8B-Instruct with llamafile-0.8 Q8_0

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 sha256:759ebc64179a445a06dfc4c44d6adfa22e389f143cc7e40e22f773420deaaaaf
3
- size 8565625440
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42b2d18996fef75c0febe43e6c316c257a460112088357b1fbcc7a4087cb36e8
3
+ size 8568574795