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.

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

关于多图片输入的问题 #111

Open
AIaimuti opened this issue Feb 18, 2025 · 2 comments
Open

关于多图片输入的问题 #111

AIaimuti opened this issue Feb 18, 2025 · 2 comments

Comments

@AIaimuti
Copy link

AIaimuti commented Feb 18, 2025

Hello, your work is great, I have some questions here about multi-image multi-round data training?

  1. Does our grpo code support multiple images and multiple rounds of data input?
  2. If not, where do you recommend to change?
@AIaimuti
Copy link
Author

Also, if the data has positive and negative sample pairs, how can grpo be trained?

@Felixvillas
Copy link

Hi~

I used R1-V in my multi images dataset, and from my perspective, the code requires only minor changes.
see in #98 (comment).

But this adaptation of mine may look ugly, please let me know if you have a new way to adapt multi-images, thanks.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants