Junyang Lin

> Dear @JustinLin610 I know you are very busy but if you give me some hints it would be very helpful! Sorry for missing this. I have just gone through...

> Dear @JustinLin610 I know you are very busy but if you give me some hints it would be very helpful! Any particular information about what you would like to...

Good. You can check the code here https://github.com/OFA-Sys/OFA/blob/main/models/ofa/unify_multihead_attention.py, and you can find the second output is the attention weight (as in line 403). I tried with your notebook, and you...

Sorry for missing again... Great! I'll look into your code once I have some free time and see if I can give you some help. Sure, you can learn about...

check https://github.com/OFA-Sys/OFA/blob/feature/add_transformers/transformers/src/transformers/models/ofa/modeling_ofa.py , the method `get_normalized_probs` should meet your demand.

The latest code or not? We've met this issue before, but we have solved it actually.

Did you install the Fairseq that we provide? I would like to check if you use the official one, which might cause problems in our code.

Thanks for pointing out the problem. Yep this might be confusing for people paying attention to details. Actually in our code we all use lowercase, but when we write the...

Would you mind checking the update on this readme https://github.com/OFA-Sys/OFA/blob/feature/add_transformers/transformers.md ? Sorry about that, I guess it might be because you are using the old generator provided by HF. We...

Sorry for my late response. To reach a similar score on the leaderboard, you should use the finetuned checkpoint. We have already released the huge ckpt of captioning for the...