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

add support for SPPO #1585

Open
wants to merge 8 commits into
base: main
Choose a base branch
from
Open

add support for SPPO #1585

wants to merge 8 commits into from

Commits on May 6, 2024

  1. add support for SPPO

    @winglian
    winglian committed May 6, 2024
    Configuration menu
    Copy the full SHA
    7fea582 View commit details
    Browse the repository at this point in the history

  2. invert check

    @winglian
    winglian committed May 6, 2024
    Configuration menu
    Copy the full SHA
    df64590 View commit details
    Browse the repository at this point in the history

  3. remove override

    @winglian
    winglian committed May 6, 2024
    Configuration menu
    Copy the full SHA
    b301068 View commit details
    Browse the repository at this point in the history

  4. bump trl

    @winglian
    winglian committed May 6, 2024
    Configuration menu
    Copy the full SHA
    60fecac View commit details
    Browse the repository at this point in the history

  5. use DPOConfig

    @winglian
    winglian committed May 6, 2024
    Configuration menu
    Copy the full SHA
    f58fcd0 View commit details
    Browse the repository at this point in the history

  6. add mistral instruct strategy and fix dpo_loss input

    @winglian
    winglian committed May 6, 2024
    Configuration menu
    Copy the full SHA
    0554105 View commit details
    Browse the repository at this point in the history

  7. update for sppo

    @winglian
    winglian committed May 6, 2024
    Configuration menu
    Copy the full SHA
    027f7d5 View commit details
    Browse the repository at this point in the history

  8. consistency w sppo -> sppo_hard

    @winglian
    winglian committed May 6, 2024
    Configuration menu
    Copy the full SHA
    6a9ac4a View commit details
    Browse the repository at this point in the history