Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Why not targets [1:-1]? #67

Open
BinZhu-ece opened this issue Nov 25, 2023 · 1 comment
Open

Why not targets [1:-1]? #67

BinZhu-ece opened this issue Nov 25, 2023 · 1 comment

Comments

@BinZhu-ece
Copy link

code/model/anyToImageVideoAudio.py line 386-387

chosen_tokens = torch.max(outputs.logits, dim=-1)[1][:, 1:-1] # [B, S-1] labels = targets[:, 2:]
@vadeli
Copy link

vadeli commented May 11, 2024

@BinZhu-ece, Same question. Did you figure it out?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@vadeli @BinZhu-ece