jartine commited on
Commit
9d52194
1 Parent(s): 05882d9

Quantize Q3_K_S with llamafile-0.8.6

Browse files
.gitattributes CHANGED
@@ -43,3 +43,4 @@ Mistral-7B-Instruct-v0.3.Q4_1.llamafile filter=lfs diff=lfs merge=lfs -text
43
  Mistral-7B-Instruct-v0.3.Q5_0.llamafile filter=lfs diff=lfs merge=lfs -text
44
  Mistral-7B-Instruct-v0.3.Q5_1.llamafile filter=lfs diff=lfs merge=lfs -text
45
  Mistral-7B-Instruct-v0.3.Q2_K.llamafile filter=lfs diff=lfs merge=lfs -text
 
 
43
  Mistral-7B-Instruct-v0.3.Q5_0.llamafile filter=lfs diff=lfs merge=lfs -text
44
  Mistral-7B-Instruct-v0.3.Q5_1.llamafile filter=lfs diff=lfs merge=lfs -text
45
  Mistral-7B-Instruct-v0.3.Q2_K.llamafile filter=lfs diff=lfs merge=lfs -text
46
+ Mistral-7B-Instruct-v0.3.Q3_K_S.llamafile filter=lfs diff=lfs merge=lfs -text
Mistral-7B-Instruct-v0.3.Q3_K_S.llamafile ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebf6f54531356b77dc0b85aaa269098ecedaaa48edc253e50e820cdaf2d287df
3
+ size 3204069551