Quantize F16 with llamafile-0.8.8
Browse files
Mixtral-8x22B-Instruct-v0.1.F16.llamafile.cat4
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 50000000000
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdb0ba33de024a8fa49f6efa47c57a43d1240ebd108f3d85edbdd45134a0455c
|
| 3 |
size 50000000000
|