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

[core] Advise to use fbs=1 #102

Merged
merged 4 commits into from
Jan 25, 2023
Merged

Conversation

younesbelkada
Copy link
Contributor

What does this PR do?

For many reasons, forward_batch_size>1 is not supported for seq2seq models and models that uses a tokenizer with padding_side="left"
As this may take some time before fixing, I propose to use forward_batch_size=1 for now and advice users to avoid using forward_batch_size>1 for now

cc @lvwerra

@younesbelkada younesbelkada changed the title [core] Advice to use fbs=1 [core] Advise to use fbs=1 Jan 24, 2023
@HuggingFaceDocBuilderDev
Copy link

HuggingFaceDocBuilderDev commented Jan 24, 2023

The documentation is not available anymore as the PR was closed or merged.

Copy link
Member

@lvwerra lvwerra left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Perfect, thank you!

@younesbelkada younesbelkada merged commit ee1ce32 into huggingface:main Jan 25, 2023
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

Successfully merging this pull request may close these issues.

3 participants