fix: llama4 conversion script no_rope_layers

[jmkuebler]

What does this PR do?

no_rope_layers should either be a list of NoPE layers or None, such that it is created in the config from the no_rope_layer_interval, see https://github.com/huggingface/transformers/blob/main/src/transformers/models/llama4/configuration_llama4.py#L338-L343

Fixes (incompatibility issue)

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 or the forum? Please add a link
  to it if that's the case.
• Did you make sure to update the documentation with your changes? Here are the
  documentation guidelines, and
  here are tips on formatting docstrings.
• 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.

@ArthurZucker @Vaibhavs10

[github-actions]

Hi 👋, thank you for opening this pull request! The pull request is converted to draft by default. The CI will be paused while the PR is in draft mode. When it is ready for review, please click the Ready for review button (at the bottom of the PR page). This will assign reviewers and trigger CI.

[pcuenca]

Thanks a lot @jmkuebler for the PR and the investigation in the Llama Scout repo! 🙌

You are right, the conversion script needs to be updated, and no_rope_layers should default to None, which will use the default setting (every fourth layer uses NoPE).

For more info, this PR is somewhat related too: https://github.com/huggingface/transformers/pull/37344/files

[jmkuebler]

@pcuenca I set the pr from draft to ready, but not sure this is how it should be done. Anything needed from my side still?

[pcuenca]

Yes, this is correct, merging. Thank you @jmkuebler!

[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.