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

Loading .pt into fairseq model for customisation #2

Closed
chrisdoyleIE opened this issue Apr 5, 2020 · 1 comment
Closed

Loading .pt into fairseq model for customisation #2

chrisdoyleIE opened this issue Apr 5, 2020 · 1 comment

Comments

@chrisdoyleIE
Copy link

Hi guys,

really incredible work, thank you.

May I please ask for a way of loading the available checkpoints into its fairseq model, such that someone can build upon your architecture?

Specifically, the "bpe" and "bpe_codes" arguments as below are what I'm trying to identify.

Screenshot 2020-04-05 at 13 59 44

@chrisdoyleIE
Copy link
Author

Solution:

The only required arguments concern the .pt itself for fairseq.TransformModel.from_pretrained(), so the snippet in the issue itself is sufficient, without reference to bpe.

The below snippet is the definition for fairseq.BaseFairseqModel.from_pretrained()

Screenshot 2020-04-05 at 14 10 24

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

1 participant