Transformers
llamafile
mixtral
jartine commited on
Commit
8f950e1
1 Parent(s): ad4453f

Quantize mixtral-8x7b-instruct-v0.1 with llamafile-0.7 Q4_0

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 sha256:4cb63b9b8013d867ed53b4e988938396919166d1a658cd9109639b97cb466fec
3
- size 26475368842
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f873ee85f74b806e574355ec8a49432f853ca6f1d774b378cf2e40fd4447ce46
3
+ size 26467897843