Quantize F16 with llamafile-0.9.0
Browse files
Meta-Llama-3.1-70B-Instruct.F16.cat0.llamafile
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 sha256:9f54fff8495bf9717d9f73c84dde3898ad23ab574cc504f98abfa99921cbd6b1
|
| 3 |
size 50000000000
|