Quantize F16 with llamafile-0.8.9
Browse files
Mistral-7B-Instruct-v0.3.F16.llamafile
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14527445248
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b527ee9ee48ce658fe48ea38d1cc474f287222fed3e98bb243d3640366623c4
|
3 |
size 14527445248
|