Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: huggingface/trl
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: v0.23.0
Choose a base ref
...
head repository: huggingface/trl
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: v0.23.1
Choose a head ref
  • 7 commits
  • 6 files changed
  • 8 contributors

Commits on Oct 2, 2025

  1. ♨️ [GRPO] Fix potential hang in get_high_entropy_mask (#4041)

    @akakakakakaa @qgallouedec
    akakakakakaa authored and qgallouedec committed Oct 2, 2025
    Configuration menu
    Copy the full SHA
    535a967 View commit details
    Browse the repository at this point in the history

  2. Aux loss is already included in the loss returned by Transformers (#4078 

    )
    @pramodith @qgallouedec
    pramodith authored and qgallouedec committed Oct 2, 2025
    Configuration menu
    Copy the full SHA
    d7283cd View commit details
    Browse the repository at this point in the history

  3. Fix get_peft_model() so that prepare_model_for_kbit_training does not… 

    … reapply to an instance of PeftModel, thus freezing all the layers (#4081)

Co-authored-by: Hoesu <[email protected]>
Co-authored-by: Kashif Rasul <[email protected]>
    @Hoesu @kashif @qgallouedec
    3 people authored and qgallouedec committed Oct 2, 2025
    Configuration menu
    Copy the full SHA
    5fb8f4c View commit details
    Browse the repository at this point in the history

  4. 🐯 fix: use_liger_kernel with IterableDataset (#4087) 

    Co-authored-by: Quentin Gallouédec <[email protected]>
Co-authored-by: Quentin Gallouédec <[email protected]>
    @jue-jue-zi @qgallouedec
    3 people committed Oct 2, 2025
    Configuration menu
    Copy the full SHA
    498422c View commit details
    Browse the repository at this point in the history

  5. [SFTrainer]: Fix DFT Loss (#4112) 

    Co-authored-by: Quentin Gallouédec <[email protected]>
    @pramodith @qgallouedec
    pramodith and qgallouedec committed Oct 2, 2025
    Configuration menu
    Copy the full SHA
    c8315d3 View commit details
    Browse the repository at this point in the history

  6. ⚡ Fix Flash Attention x Padding-Free loss (#4170)

    @qgallouedec
    qgallouedec committed Oct 2, 2025
    Configuration menu
    Copy the full SHA
    c9d103c View commit details
    Browse the repository at this point in the history

  7. Release: 0.23.1

    @qgallouedec
    qgallouedec committed Oct 2, 2025
    Configuration menu
    Copy the full SHA
    4529a1c View commit details
    Browse the repository at this point in the history
Loading