Quantize mixtral-8x7b-instruct-v0.1 with llamafile-0.8.4 F16
Browse files
mixtral-8x7b-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 43438294191
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83c2e3e625d205b7fbd318a55a6b4d5f3fdfa397f5e43fd3cf44d9938f390d06
|
| 3 |
size 43438294191
|