Quantize Q8_0 with llamafile-0.8.7
Browse files
Mixtral-8x22B-Instruct-v0.1.Q8_0.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:e50f445d729d74c3815ffd7b91f706118a5ff01305a5e630affc4fb563623e23
|
| 3 |
size 50000000000
|