jartine commited on
Commit
36be1fe
1 Parent(s): 0cf1520

Quantize Q4_K_M with llamafile-0.8.9

Browse files
Meta-Llama-3-8B-Instruct.Q4_K_M.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86fd89a017a7c3b3d27894d614198ccca8ee7a7a6f71b57c60440e68c9ba4041
3
- size 4946540852
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f2283262a7a07684892bfadffbbdfd4e881179eaa5ec8b7717906e5796787bd
3
+ size 4950931850