encoder-agnostic-adaptation icon indicating copy to clipboard operation
encoder-agnostic-adaptation copied to clipboard

Published 20 hours ago • verified publisher icon harvardnlp

Image captioning with GPT-2 1.5B

Open ftarlaci opened this issue 5 years ago • 1 comments

Are you planning on using the biggest GPT-2 for the image captioning model you are working on?

ftarlaci avatar Dec 18 '19 19:12 ftarlaci

Thanks for the question! We're not planning on using the 1.5B model for captioning at the moment, as we're working on other things (and there are non-trivial compute constraints when using the 1.5B model). That being said, you're welcome to try it out!

lukemelas avatar Dec 18 '19 19:12 lukemelas