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

How did the length extrapolation perform in Figure 5 ? #415

Open
SCZwangxiao opened this issue Oct 17, 2024 · 0 comments
Open

How did the length extrapolation perform in Figure 5 ? #415

SCZwangxiao opened this issue Oct 17, 2024 · 0 comments

Comments

@SCZwangxiao
Copy link

In Figure 5 of the technical report (which illustrates the length extrapolation capability of Qwen2-VL-72B on Video-MME Medium Video), the inference sequence length is scaled into 80K. However, the max_position_embeddings in the config is only 32768.

Could the authors share with us how did the length extrapolation perform?
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
1 participant
@SCZwangxiao