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

Tutorial on how to extract reformer layers as tf.layers #522

Closed
gaceladri opened this issue Apr 27, 2020 · 1 comment
Closed

Tutorial on how to extract reformer layers as tf.layers #522

gaceladri opened this issue Apr 27, 2020 · 1 comment

Comments

@gaceladri
Copy link

hello, do you have any tutorial on how to extract the reversible self attention layer as a tf.layer? Is it possible? Could it be possible to just take the self attention layer and integrate it to Bert? It would be amazing! Or any tutorial on bow to integrate jax with tf also will be amazing. Thanks!

@lukaszkaiser
Copy link
Contributor

We don't have a tutorial yet and it only works with reference_code=True for LSH attention, but you can already get a Keras layer out of it using this file: https://github.com/google/trax/blob/master/trax/trax2keras.py#L60

More support and tests coming!

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

2 participants