change tf.math.divide with int(/) in distilbert model

[yis11178]

What does this PR do?

This PR changes tf.math.divide with int( / ) for variable dim_per_head. Originally dim_per_head is returned as a float64 tensor and is included in the TF graph. This is not supported by some machines and there is not a solid reason to include it into the TF graph. Hence, this PR removes it from the TF graph and allows for better compatibility with user's device.

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?

@Rocketknight1

[Rocketknight1]

This is a simple change with a clear rationale, and all tests pass, so I'm happy to merge it. Thank you for this PR!