[Fix] Add original_max_position_embeddings to YARN rope_scaling optional keys

[JustinTong0323]

What does this PR do?

This PR adds support for the original_max_position_embeddings parameter in YARN rope scaling configurations, addressing compatibility issues with Qwen-32B series models.

The Qwen team requires this parameter for their YARN implementation in Qwen-32B models, ref: link.

Previously, transformers would raise warnings about unrecognized keys despite this being a valid configuration parameter:

"rope_scaling": {
    "factor": 4.0,
    "original_max_position_embeddings": 32768,  # Previously unrecognized
    "type": "yarn"
}

Impact of this PR:

• Eliminates spurious warnings for Qwen-32B users
• Enables proper configuration validation for YARN-based models

This PR could also solves downstream issues:
sgl-project/sglang#4145
vllm-project/vllm#10293

Clarify #33783

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.

[github-actions]

Hi 👋, thank you for opening this pull request! The pull request is converted to draft by default. When it is ready for review, please click the Ready for review button (at the bottom of the PR page).

[ArthurZucker]

Sure ! Thanks for finding this 🤗