jartine commited on
Commit
9856fbf
·
verified ·
1 Parent(s): 0edbc9c

Quantize Mixtral-8x22B-Instruct-v0.1 with llamafile-0.8.4 Q4_K_S

Browse files
.gitattributes CHANGED
@@ -47,3 +47,4 @@ Mixtral-8x22B-Instruct-v0.1.Q8_0.llamafile.cat1 filter=lfs diff=lfs merge=lfs -t
47
  Mixtral-8x22B-Instruct-v0.1.Q8_0.llamafile.cat2 filter=lfs diff=lfs merge=lfs -text
48
  Mixtral-8x22B-Instruct-v0.1.Q3_K_S.llamafile.cat0 filter=lfs diff=lfs merge=lfs -text
49
  Mixtral-8x22B-Instruct-v0.1.Q3_K_S.llamafile.cat1 filter=lfs diff=lfs merge=lfs -text
 
 
47
  Mixtral-8x22B-Instruct-v0.1.Q8_0.llamafile.cat2 filter=lfs diff=lfs merge=lfs -text
48
  Mixtral-8x22B-Instruct-v0.1.Q3_K_S.llamafile.cat0 filter=lfs diff=lfs merge=lfs -text
49
  Mixtral-8x22B-Instruct-v0.1.Q3_K_S.llamafile.cat1 filter=lfs diff=lfs merge=lfs -text
50
+ Mixtral-8x22B-Instruct-v0.1.Q4_K_S.llamafile.cat0 filter=lfs diff=lfs merge=lfs -text
Mixtral-8x22B-Instruct-v0.1.Q4_K_S.llamafile.cat0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78d6b3cdac750c4329805f2455e6094dd301f52304258c0035e8d28e9af82b77
3
+ size 50000000000