Quantize Q8_0 with llamafile-0.8.16
Browse files- .gitattributes +1 -0
- gemma-2-9b-it.Q8_0.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 |
gemma-2-9b-it.Q6_K.llamafile filter=lfs diff=lfs merge=lfs -text
|
| 37 |
gemma-2-9b-it.Q5_0.llamafile filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
gemma-2-9b-it.Q6_K.llamafile filter=lfs diff=lfs merge=lfs -text
|
| 37 |
gemma-2-9b-it.Q5_0.llamafile filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
gemma-2-9b-it.Q8_0.llamafile filter=lfs diff=lfs merge=lfs -text
|
gemma-2-9b-it.Q8_0.llamafile
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8adf0c22e4ac5754f6734961e7409ac318174f56dca24416e2caf3db7e14b014
|
| 3 |
+
size 9997072537
|