jartine commited on
Commit
34763ef
·
verified ·
1 Parent(s): da723a9

Quantize Q5_K_M with llamafile-0.9.0

Browse files
Mistral-7B-Instruct-v0.3.Q5_K_M.llamafile CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0758ae3bcea224fd378785ca871bb99210216271b5fc39c6e8c48627cfc15035
3
- size 5165955342
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f012dbcb4604ef1482e0b6f869440103df20319e6007c7587d741ccf2ca86014
3
+ size 5379019064