Update `is_floating_point()` docs to mention bfloat16 (#49611)
Summary:
Fixes https://github.com/pytorch/pytorch/issues/49610 . Explicitly mentions that `is_floating_point()` will return `True` if passed a `bfloat16` tensor.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/49611
Reviewed By: mrshenli
Differential Revision: D25660723
Pulled By: VitalyFedyunin
fbshipit-source-id: 04fab2f6c1c5c2859c6efff1976a92a676b9efa3
