Support Clip QKV for MPT

[akakakakakaa]

What does this PR do?

• Support Clip QKV for MPT

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?

@ArthurZucker and @younesbelkada

[younesbelkada]

Thanks for this - @ArthurZucker indeed clip_qkv seems to be always there in MPTConfig: https://huggingface.co/mosaicml/mpt-7b/blob/main/config.json#L12 /

transformers/src/transformers/models/mpt/configuration_mpt.py

Line 48 in bdf36dc

clip_qkv (`float`, *optional*):

but we never used it

[akakakakakaa]

@younesbelkada
Is there any issue with merging this PR? Looking at the failed tests, it doesn't seem to be a problem with the PR code.

[younesbelkada]

Yes this looks good for me, just waiting for final core maintainer review
cc @amyeroberts @ArthurZucker

[amyeroberts]

Thanks for adding this support!