jartine commited on
Commit
6e01ba0
1 Parent(s): a11a92b

Quantize Phi-3-mini-4k-instruct with llamafile-0.8.1 BF16

Browse files
.gitattributes CHANGED
@@ -48,3 +48,4 @@ Phi-3-mini-4k-instruct.Q4_K_M.llamafile filter=lfs diff=lfs merge=lfs -text
48
  Phi-3-mini-4k-instruct.Q5_K_S.llamafile filter=lfs diff=lfs merge=lfs -text
49
  Phi-3-mini-4k-instruct.Q5_K_M.llamafile filter=lfs diff=lfs merge=lfs -text
50
  Phi-3-mini-4k-instruct.Q6_K.llamafile filter=lfs diff=lfs merge=lfs -text
 
 
48
  Phi-3-mini-4k-instruct.Q5_K_S.llamafile filter=lfs diff=lfs merge=lfs -text
49
  Phi-3-mini-4k-instruct.Q5_K_M.llamafile filter=lfs diff=lfs merge=lfs -text
50
  Phi-3-mini-4k-instruct.Q6_K.llamafile filter=lfs diff=lfs merge=lfs -text
51
+ Phi-3-mini-4k-instruct.BF16.llamafile filter=lfs diff=lfs merge=lfs -text
Phi-3-mini-4k-instruct.BF16.llamafile ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cc2cd6918ea05fc992d9e4731baca445e7ebd968fcbdbb462e02449091b5801
3
+ size 7671518174