目前为止对大模型原理的最佳介绍,这就是世界级专家的水平,知道介绍什么,知道在什么抽象层次介绍, 不会让不懂的人陷入毫无意义的细节,对重要概念的理解又不会缺失,实在是太精彩了。https://www.youtube.com/watch?v=7xTGNNLPyMI&t=3s
Deep Dive into LLMs like ChatGPT
This is a general audience deep dive into the Large Language Model (LLM) AI technology that powers ChatGPT and related products. It is covers the full training stack of how the models are developed, along with mental models of how to think about their "psychology"…






























