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

Add ParametricAttention.v2 #913

Merged
merged 7 commits into from
Dec 14, 2023

Commits on Dec 12, 2023

  1. Add ParametricAttention.v2

    This layer is an extension of the existing `ParametricAttention` layer,
    adding support for transformations (such as a non-linear layer) of the
    key representation. This brings the model closer to the paper that
    suggested it (Yang et al, 2016) and gave slightly better results in
    experiments.
    danieldk committed Dec 12, 2023
    Configuration menu
    Copy the full SHA
    a2e178f View commit details
    Browse the repository at this point in the history

Commits on Dec 13, 2023

  1. Configuration menu
    Copy the full SHA
    f394c84 View commit details
    Browse the repository at this point in the history
  2. Remove stray import

    danieldk committed Dec 13, 2023
    Configuration menu
    Copy the full SHA
    137a457 View commit details
    Browse the repository at this point in the history
  3. Configuration menu
    Copy the full SHA
    e92d581 View commit details
    Browse the repository at this point in the history
  4. Configuration menu
    Copy the full SHA
    06be6dd View commit details
    Browse the repository at this point in the history
  5. isooooooort

    danieldk committed Dec 13, 2023
    Configuration menu
    Copy the full SHA
    2369b34 View commit details
    Browse the repository at this point in the history
  6. Update citation to ACL link

    Co-authored-by: Adriane Boyd <[email protected]>
    svlandeg and adrianeboyd authored Dec 13, 2023
    Configuration menu
    Copy the full SHA
    80f47b7 View commit details
    Browse the repository at this point in the history