You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi, thanks for your amazing work!
I've found that the inputs to 'get_per_token_logps' for model and ref_model are different, which might lead to a critical bug. This bug appears in R1-mulitimodal and Open-R1-Video. I've documented my understanding in this blog Hui-design/R1-Video-fixbug. Could you please review it to see if my understanding is correct?
The text was updated successfully, but these errors were encountered:
Hi, thanks for your amazing work!
I've found that the inputs to 'get_per_token_logps' for model and ref_model are different, which might lead to a critical bug. This bug appears in R1-mulitimodal and Open-R1-Video. I've documented my understanding in this blog Hui-design/R1-Video-fixbug. Could you please review it to see if my understanding is correct?
The text was updated successfully, but these errors were encountered: