Quantize BF16 with llamafile-0.8.11
Browse files
Mistral-7B-Instruct-v0.3.BF16.llamafile
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:913590cf311ca7cee7eee46df2594bf677d14ef202237a0a9ef783ad6801843c
|
3 |
+
size 14527117578
|