Transformers
llamafile
mixtral
jartine commited on
Commit
b321c10
1 Parent(s): 0191dbf

Quantize mixtral-8x7b-instruct-v0.1 with llamafile-0.8.2 Q6_K

Browse files
mixtral-8x7b-instruct-v0.1.Q6_K.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d6bee444cf59f5d5e813fdd05c5679699b9acc0705f719886af02829428b0db
3
- size 38405149171
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae26ff5b3c13498d232200a06f13d267eec1f7880d0bac33230b63adb4f463c9
3
+ size 38410139825