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

Fixing the projection layer when using weight tying and dim from Transformer output and item embedding differs #689

Merged
merged 1 commit into from
Apr 27, 2023

Conversation

gabrielspmoreira
Copy link
Member

@gabrielspmoreira gabrielspmoreira commented Apr 27, 2023

Fixes the projection when using weight tying, as it should not use an activation function, as found by @bschifferer

…ctivation function to match the distribution of item embeddings
@gabrielspmoreira gabrielspmoreira requested review from sararb and bschifferer and removed request for sararb April 27, 2023 14:34
@gabrielspmoreira gabrielspmoreira self-assigned this Apr 27, 2023
@gabrielspmoreira gabrielspmoreira added the bug Something isn't working label Apr 27, 2023
@gabrielspmoreira gabrielspmoreira added this to the Merlin 23.04 milestone Apr 27, 2023
@github-actions
Copy link

@gabrielspmoreira gabrielspmoreira merged commit 72ede98 into main Apr 27, 2023
@rnyak rnyak deleted the weight_tying_fix branch April 27, 2023 16:15
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants