Quantize Q6_K with llamafile-0.8.8
Browse files
Mixtral-8x22B-Instruct-v0.1.Q6_K.llamafile.cat0
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:f34b68aa21c296858fc5ad07f8bfd4b625580f35bdbbe7dab5a7ae3d8915857f
|
| 3 |
size 50000000000
|