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.

Sign up for GitHub

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

Jump to bottom

Texts based on different prefixes = hanging #144

Open
metroshlam opened this issue Dec 1, 2019 · 1 comment
Open

Texts based on different prefixes = hanging #144

metroshlam opened this issue Dec 1, 2019 · 1 comment

Comments

@metroshlam
Copy link

metroshlam commented Dec 1, 2019 •
edited
Loading

Hi!
Gpt2simple works fine when one needs to generate a batch of similar texts, for instance, using a pre-trained model + one prefix.

While trying to gen for instance 100 texts from 100 intros face hanging the system during 3-5th cycle step. Guess that's because of memory leaks when opening/closing the generation sessions.

Is it possible to proceed with the only generation session and send a row of prepend texts to obtain a number of different texts during the only step?
@hafsahabib-educator
Copy link

@metroshlam did you find a solution ?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@hafsahabib-educator @metroshlam