25 Jul 2024
8m
【transformer面试宝典】4 multi head self attention中为啥OKV要用三个不同的矩阵 代码讲解，搞定面试！卢菁博士#人工智能 #transformers
Dr.LuAIclass 卢菁 北大博士后 AI 专家
Open in Podwise to generate AI notes
Sign in to process this episode and unlock summaries, transcripts, highlights and translations.
Shownotes are not generated by Podwise.