Model load fix for qwen2 0.5b and 1.5b

[matvey-kolbasov-hs]

Fix for Qwen2 model loading

This PR fixes an issue with loading for models Qwen2 0.5B and Qwen2 1.5B. These models use tied embeddings so they require corresponding aliases for layer names.

• 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?

[danieldk]

Thanks for reporting this and providing a PR!

Since the model configuration states whether the embeddings are tied or not, I think it's nicer to rely on the configuration rather than aliases.

See #2313.

[danieldk]

Fixed by #2313. Thanks again for pointing out this issue and providing a fix!