Transformers
llamafile
mixtral
jartine commited on
Commit
5011535
1 Parent(s): 08e9ed0

Quantize mixtral-8x7b-instruct-v0.1 with llamafile-0.8 Q2_K

Browse files
mixtral-8x7b-instruct-v0.1.Q2_K.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28a25d3243eb896d4287160b362a44b3fba2373f1b2b2b243c246b604701ea71
3
- size 15677919626
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd3d7dbe9d0ff27e16f01298ed7cb38d56711c9c1ed6a7184e8d56d1c7aa481f
3
+ size 17338340073