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

Transfoxl seq classification #8868

Merged

Conversation

spatil6
Copy link
Contributor

@spatil6 spatil6 commented Dec 1, 2020

This PR implements Sequence classification for Transformer XL model
TransfoxlForSequenceClassification uses the last token in order to do the classification, as other causal models (e.g. GPT-1,GPT-2) do.

Fixes #7623 (Partially)

Before submitting

  • This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
  • Did you read the contributor guideline,
    Pull Request section?
  • Was this discussed/approved via a Github issue or the forum? Please add a link
    to it if that's the case.
  • Did you make sure to update the documentation with your changes? Here are the
    documentation guidelines, and
    here are tips on formatting docstrings.
  • Did you write any new necessary tests?

Who can review?

@LysandreJik

Copy link
Member

@LysandreJik LysandreJik left a comment

Choose a reason for hiding this comment

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

LGTM, thanks a lot @spatil6!

Same as GPT-2, this would benefit from also handling padding on the left; I'll work on this in another PR.

Copy link
Collaborator

@sgugger sgugger left a comment

Choose a reason for hiding this comment

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

Thanks a lot for adding this!

@@ -632,6 +633,40 @@ class TransfoXLModelOutput(ModelOutput):
attentions: Optional[Tuple[torch.FloatTensor]] = None


@dataclass
class TransfoXLSequenceClassifierOutputWithPast(ModelOutput):
Copy link
Collaborator

Choose a reason for hiding this comment

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

This new class needs to be documented in the .rst with the other TransfoXL-specific outputs.

batch_size, sequence_length = inputs_embeds.shape[:2]

assert (
self.config.pad_token_id is not None or batch_size == 1
Copy link
Contributor

Choose a reason for hiding this comment

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

great assert!

Copy link
Member

Choose a reason for hiding this comment

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

thanks!

Copy link
Contributor

@patrickvonplaten patrickvonplaten left a comment

Choose a reason for hiding this comment

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

Good to merge for me

@LysandreJik LysandreJik merged commit f6b44e6 into huggingface:master Dec 2, 2020
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.

Implement PyTorch and/or TensorFlow sequence classification architectures for causal language models
4 participants