Transformers
llamafile
mixtral
jartine commited on
Commit
b581c66
1 Parent(s): 21c35bf

Quantize Q4_0 with llamafile-0.8.7

Browse files
mixtral-8x7b-instruct-v0.1.Q4_0.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51ed420805ea28d519cd8dce770fbf519dc4cb9700039bd546875a82abdcb8d6
3
- size 26479114338
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2afd5ca65d382d1dded09430c6449f8794de3a2933a6370fd11a60b02d95dd03
3
+ size 26469283939