Transformers
llamafile
mixtral
jartine commited on
Commit
d67d18e
1 Parent(s): 88e7243

Quantize Q4_K_M with llamafile-0.8.5

Browse files
mixtral-8x7b-instruct-v0.1.Q4_K_M.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f5f0e5ea8c1988baa06623d4a9f7d92ca2babdae1127d4447562d8c89247d3a
3
- size 28477831349
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c2859c9288d0d7ca6483b80ca88f6a121b35ab44755c38491b35a35eb42e4f8
3
+ size 28483991654