Quantize F16 with llamafile-0.8.7
Browse files
Mixtral-8x22B-Instruct-v0.1.F16.llamafile.cat2
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 sha256:38ff6175984c2e5d3d3b26e1a9345b670e7f0c82d79fc83e31afc40a4a2ca079
|
| 3 |
size 50000000000
|