Add Fine-Tuning a Vision Language Model with TRL using MPO recipe

[sergiopaniego]

What does this PR do?

Add Fine-Tuning a Vision Language Model with TRL using MPO recipe

Fixes #317

Who can review?

@merveenoyan and @stevhliu

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[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.

[review-notebook-app]

View / edit / reply to this conversation on ReviewNB

stevhliu commented on 2025-07-21T18:47:56Z
----------------------------------------------------------------

I think this loss_type list is more appropriate in section 3.3 and you probably don't need to list all possible types - only list the ones you'll use and refer the reader to the docs for more

[review-notebook-app]

View / edit / reply to this conversation on ReviewNB

stevhliu commented on 2025-07-21T18:47:57Z
----------------------------------------------------------------

I think maybe this needs to be in English 😁

[stevhliu]

Really cool, thanks for the new recipe!

[sergiopaniego]

Ready for review as MPO PR in trl is already merged!

Thanks for the comments @stevhliu. I've addressed them.