News for hackers. Stuff that matters.

A comment on Understanding and Coding the Self-Attention Mechanism of Large Language Models. Parent comment

Re:Understanding and Coding the Self-Attention Mechanism of ... by GaggiX on Friday February 10, 2023 @07:39PM (#34748153)
This article explains well why we need attention: https://jalammar.github.io/visualizing-neural-machine-transl..., and also how it was developed.
[ Parent | on HN ]
Re:Understanding and Coding the Self-Attention Mechanism of ... by zmmmmm on Friday February 10, 2023 @08:13PM (#34748428)
those animations are beautiful!
[ Parent | on HN ]