Quantize F16 with llamafile-0.8.9
Browse files
mixtral-8x7b-instruct-v0.1.F16.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:c6f56fabfa9539f99907627b76f3205b42a098b1847831e1b506bc334b0cd6ad
|
| 3 |
size 50000000000
|