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.

Sign up for GitHub

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

Jump to bottom

[Fix] Name generalization of transformer blocks #44

Merged
merged 2 commits into from
Nov 27, 2023
Merged

[Fix] Name generalization of transformer blocks #44

merged 2 commits into from
Nov 27, 2023

Commits on Nov 26, 2023

  1. generalize block name finding 

    Since the name of a transformer block (start and end nodes) can follow the pattern model_layers_X (for mistral) or transformer_h_X we must generalize it.

Co-Authored-By: Daniel Grittner <[email protected]>
    @abourramouss @danielgrittner
    abourramouss and danielgrittner committed Nov 26, 2023
    Configuration menu
    Copy the full SHA
    46339ba View commit details
    Browse the repository at this point in the history

  2. Merge branch 'xrsrke:main' into main

    @abourramouss
    abourramouss authored Nov 26, 2023
    Configuration menu
    Copy the full SHA
    40a7ede View commit details
    Browse the repository at this point in the history