jartine commited on
Commit
6a8402d
1 Parent(s): 0a74e09

Quantize F16 with llamafile-0.8.9

Browse files
Meta-Llama-3-8B-Instruct.F16.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a68e497492d592cceb348ea1ae961d3a810125b9ec18d7d298798e944368330f
3
- size 16094673198
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bcdd9daeb5fd55b14cc173d0173e7caa185350d8a314a93159589870caae70f
3
+ size 16099064196