About input text token max_length
lyakaap opened this issue · comments
Great work!
I noticed max_length is set to 25 here, which is much smaller than 77 of CLIP.
How do you derive this setting?
Hi, thanks for you interest in our paper.
This setting is determined by (1) the average sentence length of the pre-training dataset and (2) computational efficiency.
Feel free to let me know if you might have any other questions/suggestions. Thanks.
Thank you very much for your answer!