convert_beam_search supports large gpt2 model (#11989)
(1) add --run_shape_inference to make shape inference optional
(2) add --vocab_mask to make the input optional
(3) add --overwrite in gpt2 convert_to_onnx to allow overwrite existed raw onnx from PyTorch
(4) save gpt2 model tensors to one external data file by default
(5) group convert_beam_search arguments to multiple groups
(6) make --decoder_onnx optional for gpt2 model
(7) replace print by logger
(8) update shape inference function to support external data.
(9) when saving external data, show warning if onnx version < 1.12
