谷歌提出的Transformer结构tput Probabilities Softmax Linear Add& Norm Feed orwa Add& Norm Add norm Multi-Head Attention Forward N Add Norm I Add norm Masked Multi-Head Multi-Head Attention Atention Encoding ① Encoding ut Output Embedding Embedding Inputs Ish

《Attention is All You Need》中文版，自己学习时翻译的，不想下载的同学可以去我的blog看：https://blog.csdn.net/nocml/article/details/103082600