jartine commited on
Commit
81b4813
·
verified ·
1 Parent(s): e4a2599

Quantize Q8_0 with llamafile-0.8.8

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 sha256:8ccf804f6f45ad751a0f0fc9500230b27f2b1cced25f8e359bb8bb9b06d54b1f
3
- size 7728281772
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdf97046d62f2ad425afd3f7dffb9cdebd92fc3b0c75acb5c33e18efe88a0576
3
+ size 7732672770