Transformer 模型详解
https://baijiahao.baidu.com/s?id=1651219987457222196&wfr=spider&for=pc
Word Embedding
https://my.oschina.net/earnp/blog/1113896
如何理解Transformer论文中的positional encoding,和三角函数有什么关系
https://www.zhihu.com/question/347678607/answer/864217252
深入理解Transformer及其源码
https://www.cnblogs.com/zingp/p/11696111.html#_label5