Quantize F16 with llamafile-0.8.8
Browse files
Mixtral-8x22B-Instruct-v0.1.F16.llamafile.cat1
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 sha256:91ae44ece48b9383eb549e17862a92918646a4c4b442b40e9d0a2abaf3df98b4
|
3 |
size 50000000000
|