jartine commited on
Commit
1550162
1 Parent(s): 7f67764

Quantize BF16 with llamafile-0.8.7

Browse files
.gitattributes CHANGED
@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
36
  llm-compiler-13b-ftd.Q5_0.llamafile filter=lfs diff=lfs merge=lfs -text
37
  llm-compiler-13b-ftd.Q6_K.llamafile filter=lfs diff=lfs merge=lfs -text
38
  llm-compiler-13b-ftd.F16.llamafile filter=lfs diff=lfs merge=lfs -text
 
 
36
  llm-compiler-13b-ftd.Q5_0.llamafile filter=lfs diff=lfs merge=lfs -text
37
  llm-compiler-13b-ftd.Q6_K.llamafile filter=lfs diff=lfs merge=lfs -text
38
  llm-compiler-13b-ftd.F16.llamafile filter=lfs diff=lfs merge=lfs -text
39
+ llm-compiler-13b-ftd.BF16.llamafile filter=lfs diff=lfs merge=lfs -text
llm-compiler-13b-ftd.BF16.llamafile ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:439844e1dd802ab2fe162e01d2ac3d18e343f6d5e6f72a7136ac023996fa536d
3
+ size 26059028654