Question about the effect of betnet50t_256 #1006
Unanswered
liuhui0401
asked this question in
Q&A
Replies: 1 comment
-
@liuhui0401 yes, it's different I needed to use fewer blocks with the bottleneck attention so it ran reasonable on limited GPU machines, everything is there to create something closer to the paper by adding a different model definition. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
I wonder that is the effect of botnet50t_256 the same as the paper? I noticed that the structure of this model is not the same as the paper.
Beta Was this translation helpful? Give feedback.
All reactions