onnxruntime

optimize a bert model converted using tf2onnx (#5492)

* optimize a bert model converted using tf2onnx

* add test data

* update

* remove comments

* format

* Revert "format"

This reverts commit f8ae88cb564bce5caf4780e56561403f3ba3d524.

* Revert "remove comments"

This reverts commit 59d8a693581a731fd0291b70fe2c9cec6c4950fe.

* add a squeeze node to convert a 3-d mask to 2-d

* update

* update

* verify and add comments