jartine commited on
Commit
85937fb
·
verified ·
1 Parent(s): 2086c18

Quantize Q6_K with llamafile-0.8.13

Browse files
Meta-Llama-3.1-8B-Instruct.Q6_K.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5a74ecd0f015505d56f8ff898502edcb00467fcc334a1b2d80210641206f2c6
3
- size 6625835266
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a3a5823016506a041adeb51b61c341b60e019df9b22838546add664f0b8510c
3
+ size 6837516554