Discover How LLMs Work by Dissecting Llama

In this video, I explain AI models from first principles, at a level of abstraction that is easy to understand if you're a generalist software engineer or just a little tech-savvy. In only 10 minutes, we'll cover AI models & LLMs and dive deep into the Llama model. We'll even change its internals to generate special Haiku's, which the original Llama 1B model can't do.

You can follow along using this Colab notebook:
https://colab.research.google.com/drive/1P8O19FYnkHAASM5pz0RE8HnD6rCBVmmK?usp=sharing

And here is a list of common ambiguous phrases people use in the context of LLMs, together with their explanations:
https://docs.google.com/document/d/1q9_-6UHcjWa_mr1RdbNYcTMNqsBUV_XGqGiXma2dk-o/edit?usp=sharing

Let me know what topics you'd like me to cover next!

00:00 Intro
00:45 AI models explained
02:41 LLMs explained
03:48 Intro the Llama model family
05:02 The Llama model architecture
07:51 Surgery on Llama to generate special Haiku's

Видео Discover How LLMs Work by Dissecting Llama канала Julia Turc