self-attention transformer
一、What is sequence transduction models?
What is Sequence Transduction? ? Any task where input sequences are transformed into output. sequences. ? Practical examples: speech recognition, text-to-speech, machine.
二、讲qkv，而且有代码
https://zhuanlan.zhihu.com/p/410776234
三、讲transformer的
https://zhuanlan.zhihu.com/p/411311520