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

Flan-T5 #75

Open
Bachstelze opened this issue May 3, 2023 · 2 comments
Open

Flan-T5 #75

Bachstelze opened this issue May 3, 2023 · 2 comments

Comments

@Bachstelze
Copy link

Can we use FLAN-T5 as a language model?
Those FLAN models can represent English and other languages significantly better in our tests.
"If you already know T5, FLAN-T5 is just better at everything. For the same number of parameters, these models have been fine-tuned on more than 1000 additional tasks covering also more languages."

@phalexo
Copy link

phalexo commented May 3, 2023

Wouldn't you have to retrain text to image models because the representations are different?

@darkman111a
Copy link

Yes, could expertiment with finetuning once you swap it out. I'm 1000% sure FLAN-T5 would result in higher fidelity output, better composition, way better spatial awareness. I think "tango model" kind of validates this.

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

3 participants