Created by: lcy-seso

• implement they layer normalization operator and the Python wrapper.
  • CPU implementation.
  • GPU implementation.
  • python wrapper.
• enhance the matmul operator to support 4-D tensor as its inputs https://github.com/PaddlePaddle/Paddle/issues/7319. fixed by PR: https://github.com/PaddlePaddle/Paddle/pull/7656
• prepare the dataset.
  fixed by PR: https://github.com/PaddlePaddle/Paddle/pull/7661
• wrap the masked positional embedding.
• enhance the lookup_table operator to support the special token: padding index. https://github.com/PaddlePaddle/Paddle/issues/7309.
• wrap the multi-head dot product attention. This is different to ConvS2S.
• wrap the positional-wise feed-forward network.
• wrap the basic computation block.
• build the entire model.
• enhance the documentation of operators used in Transformer.
• add beam search for Transformer.
• clean codes and merge the entire project into the models repo (merge the work part by part).
• Learning Rate Scheduler
• Residual Dropout
• Label Smoothing
  • label smooth operator.
  • python wrapper.
• Scaled Dot Product Attention
• Weight sharing between embedding and pre-softmax linear transformation layers