-
https://cloud.tencent.com/developer/article/2400095
-
https://baike.baidu.com/item/Transformer模型架构/64430120
-
https://mp.weixin.qq.com/s?__biz=MzU0NjgzMDIxMQ==&mid=2247624675&idx=1&sn=a772aa70bf84d385ec11ffae5d04633f&chksm=fa619827ea591f0db9423deac1d99bb0e9c29ea1b4063e0f9a72a5647365271eea9c3af63ce2&scene=27
-
https://www.woshipm.com/share/6268234.html
-
https://blog.csdn.net/CSDN_224022/article/details/151793261
-
https://zhuanlan.zhihu.com/p/1889229353243627581
-
https://blog.csdn.net/CSDN_224022/article/details/149782128
-
https://developer.aliyun.com/article/1634659?accounttraceid=4199e995720c4711a3c6064b562adf29lbki
-
https://zhuanlan.zhihu.com/p/607423406
-
https://www.zhihu.com/question/321793224/answer/125473853309?share_code=dkOHWcRLEXeF&utm_psn=1983432342640035305