jartine commited on
Commit
3288b83
1 Parent(s): 450cfb8

Quantize Q6_K with llamafile-0.8.7

Browse files
Meta-Llama-3-8B-Instruct.Q6_K.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:176a9cebccc001636b61f54d87daf9b76018f614f3d8d6fb638a94c3bc4b4b9c
3
- size 6631668015
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b45ff9c781464151b81ca9c6a833db259026f583a7170130d7310e207608deb
3
+ size 6621837616