Quantize Mixtral-8x22B-Instruct-v0.1 with llamafile-0.8.4 Q5_K_M
Browse files
Mixtral-8x22B-Instruct-v0.1.Q5_K_M.llamafile.cat2
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e4384bbaa1c1365fead8fbb294140b0bedc5f3d6e627f800bd6ef79e99f01b2
|
3 |
+
size 10440887
|