Transformers
llamafile
mixtral
jartine commited on
Commit
c0e5318
1 Parent(s): d29cbbb

Quantize BF16 with llamafile-0.8.7

Browse files
mixtral-8x7b-instruct-v0.1.BF16.llamafile.cat1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f98c477d48626aeb0e3f420ceb66509500bc05ed39ff5c62e8c7b83baf85d8d
3
- size 43444454498
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c58973676fa9ab61c72c5b8c9a8d9e60b91562f31a4aa991879084c3e6faa47e
3
+ size 43434624099