Transformers
llamafile
mixtral
jartine commited on
Commit
7dd53a1
1 Parent(s): fa079a4

Quantize Q8_0 with llamafile-0.8.12

Browse files
mixtral-8x7b-instruct-v0.1.Q8_0.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab35c700629e10e5ebabbf3ba11d7b451c226acab02f95418e7a2176b6c9e635
3
- size 49656379577
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe52b3e31c90a7a4b831c9a1b2b646c4f5dd341b9a0fbfbaa0d3308ab8aab69b
3
+ size 49656248505