Skip to content

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

Merged
gabrielspmoreira merged 1 commit intomainfrom
weight_tying_fix
Apr 27, 2023
Merged

Fixing the projection layer when using weight tying and dim from Transformer output and item embedding differs#689
gabrielspmoreira merged 1 commit intomainfrom
weight_tying_fix

Conversation

@gabrielspmoreira
Copy link
Copy Markdown
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 bschifferer and sararb 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
Copy Markdown

@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