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

(EncoderDecoderModel) Why decoder_start_token_id are different between train and generation? #14439

Closed
hansd410 opened this issue Nov 18, 2021 · 0 comments · Fixed by #14441
Closed

(EncoderDecoderModel) Why decoder_start_token_id are different between train and generation? #14439

hansd410 opened this issue Nov 18, 2021 · 0 comments · Fixed by #14441

Comments

@hansd410
Copy link

As source code given below from EncoderDecoderModel, decoder_start_token_id are different between train and generation.

>>> # training
>>> model.config.decoder_start_token_id = tokenizer.cls_token_id

>>> # generation
>>> generated = model.generate(input_ids, decoder_start_token_id=model.config.decoder.pad_token_id)

Why they are not same?
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

Successfully merging a pull request may close this issue.

Fix EncoderDecoderModel code example NielsRogge/transformers
1 participant
@hansd410