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 Model] Pairwise Preference Model #123

Merged
merged 9 commits into from
May 14, 2024

Commits on May 9, 2024

  1. Create pairpm.py

    I created a PairPMPipeline class to use the pair preference model. I also presented an example to use the preference model.
    WeiXiongUST committed May 9, 2024
    Configuration menu
    Copy the full SHA
    d7e664b View commit details
    Browse the repository at this point in the history
  2. add pairpm pipeline

    WeiXiongUST committed May 9, 2024
    Configuration menu
    Copy the full SHA
    a374ec1 View commit details
    Browse the repository at this point in the history

Commits on May 10, 2024

  1. change the name to slicpairpm

    The training and use of the models are similar to that of Slic paper SLiC-HF: Sequence Likelihood Calibration with Human Feedback.
    WeiXiongUST committed May 10, 2024
    Configuration menu
    Copy the full SHA
    f727b8c View commit details
    Browse the repository at this point in the history

Commits on May 12, 2024

  1. Update rewardbench/models/__init__.py

    Co-authored-by: Nathan Lambert <nathanl@allenai.org>
    WeiXiongUST and natolambert authored May 12, 2024
    Configuration menu
    Copy the full SHA
    b8b53e9 View commit details
    Browse the repository at this point in the history

Commits on May 13, 2024

  1. modify interface

    WeiXiongUST committed May 13, 2024
    Configuration menu
    Copy the full SHA
    a533f75 View commit details
    Browse the repository at this point in the history
  2. adjust pipeline builder

    we now use task, model, and tokenizer to init the pipeline.
    WeiXiongUST committed May 13, 2024
    Configuration menu
    Copy the full SHA
    e570d0d View commit details
    Browse the repository at this point in the history

Commits on May 14, 2024

  1. improve code quality

    WeiXiongUST committed May 14, 2024
    Configuration menu
    Copy the full SHA
    d66b833 View commit details
    Browse the repository at this point in the history
  2. Revert "improve code quality"

    This reverts commit d66b833.
    WeiXiongUST committed May 14, 2024
    Configuration menu
    Copy the full SHA
    a9f8217 View commit details
    Browse the repository at this point in the history
  3. improve style and quality

    WeiXiongUST committed May 14, 2024
    Configuration menu
    Copy the full SHA
    098aef6 View commit details
    Browse the repository at this point in the history