Quantize F16 with llamafile-0.8.7
Browse files- .gitattributes +1 -0
- llm-compiler-13b-ftd.F16.llamafile +3 -0
.gitattributes
CHANGED
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
35 |
*tfevents* 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
|
|
|
|
35 |
*tfevents* 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
|
llm-compiler-13b-ftd.F16.llamafile
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:816b99f884ec30551040df59ac7a9c76b17af12d3dce3b2b8e7685cd8d9e23dd
|
3 |
+
size 26059028652
|