Quantize mixtral-8x7b-instruct-v0.1 with llamafile-0.8.4 F16
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 sha256:265924708f35a9a1f222defe24d1277ebd43a9295b4a3169b42d9382e10b6737
|
| 3 |
size 50000000000
|