Quantize F16 with llamafile-0.8.8
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 sha256:186f68ccc76ccbf9b769e28ba4a3cf63867fe2fc40b4a584dca855deaa0371cf
|
| 3 |
size 50000000000
|