Quantize mixtral-8x7b-instruct-v0.1 with llamafile-0.8.4 BF16
Browse files
mixtral-8x7b-instruct-v0.1.BF16.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:fc32cf737232b638a7f38522d65e8df50a8fc919804ff25c1e1df7a8c23a25f3
|
| 3 |
size 50000000000
|