细讲: https://mp.weixin.qq.com/s/RLxWevVWHXgX-UcoxDS70w
https://www.jianshu.com/p/b1030350aadb
详解Transformer (Attention Is All You Need)
https://zhuanlan.zhihu.com/p/48508221
https://www.jianshu.com/p/d7f50cc5560e