llamafile
English
GGUF
jartine commited on
Commit
679b4d6
1 Parent(s): a84bff6

Quantize TinyLlama-1.1B-Chat-v1.0 with llamafile-0.7 BF16

Browse files
.gitattributes CHANGED
@@ -64,3 +64,4 @@ TinyLlama-1.1B-Chat-v1.0.Q5_1.llamafile filter=lfs diff=lfs merge=lfs -text
64
  TinyLlama-1.1B-Chat-v1.0.Q3_K.llamafile filter=lfs diff=lfs merge=lfs -text
65
  TinyLlama-1.1B-Chat-v1.0.Q4_K.llamafile filter=lfs diff=lfs merge=lfs -text
66
  TinyLlama-1.1B-Chat-v1.0.Q5_K.llamafile filter=lfs diff=lfs merge=lfs -text
 
 
64
  TinyLlama-1.1B-Chat-v1.0.Q3_K.llamafile filter=lfs diff=lfs merge=lfs -text
65
  TinyLlama-1.1B-Chat-v1.0.Q4_K.llamafile filter=lfs diff=lfs merge=lfs -text
66
  TinyLlama-1.1B-Chat-v1.0.Q5_K.llamafile filter=lfs diff=lfs merge=lfs -text
67
+ TinyLlama-1.1B-Chat-v1.0.BF16.llamafile filter=lfs diff=lfs merge=lfs -text
TinyLlama-1.1B-Chat-v1.0.BF16.llamafile ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f2c0607e66a3c3726647914aaae6b3594f8bf307522dd1c32926057d35908f6
3
+ size 2225279471