Skip to content

Conversation

sergiopaniego
Copy link
Member

What does this PR do?

Adding training scripts for GSPO (VLM/LLM).
I'll train 2 models with them with a subset of the dataset to verify but they're quite similar to grpo and grpo_vlm.

Before submitting

  • This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
  • Did you read the contributor guideline,
    Pull Request section?
  • Was this discussed/approved via a GitHub issue? Please add a link
    to it if that's the case.
  • Did you make sure to update the documentation with your changes?
  • Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

@HuggingFaceDocBuilderDev

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

@qgallouedec
Copy link
Member

Super cool and useful! Some comments about the hyperparam

@qgallouedec qgallouedec merged commit 3ae60cd into main Jul 31, 2025
11 checks passed
@qgallouedec qgallouedec deleted the gspo-scripts branch July 31, 2025 02:07
LuisVasquezBSC pushed a commit to langtech-bsc/trl that referenced this pull request Aug 28, 2025
LuisVasquezBSC pushed a commit to langtech-bsc/trl that referenced this pull request Aug 28, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants