Build A Reasoning Model From Scratch 1: Motivation & Code Setup

This video explains the relationship between conventional LLMs and reasoning models (and agents), philosophizes a about "from scratch" approaches, and explains how to install Python & PyTorch requirements with uv. - Reasoning playlist: https://www.youtube.com/watch?v=Kh9mqTzjuEQ&list=PLfrHAQCRxtUs - Reasoning Book: https://amzn.to/4aAKiFY - Reasoning GitHub repo: https://github.com/rasbt/reasoning-from-scratch - Reasoning effort article: https://magazine.sebastianraschka.com/p/controlling-reasoning-effort-in-llms - LLMs from Scratch book: https://amzn.to/4fqvn0D - LLMs from Scratch repo: https://github.com/rasbt/LLMs-from-scratch - LLMs from Scratch playlist: https://www.youtube.com/watch?v=yAcWnfsZhzo&list=PLTKMiZHVd_2IIEsoJrWACkIxLRdfMlw11&index=1 0:00 Introduction 1:16 From conventional LLMs to reasoning models 2:54 Reasoning models and agent harnesses 4:00 Why implement models from scratch? 8:23 Learning resources and books 11:42 What this video series covers 14:23 Controlling reasoning effort in modern LLMs 17:19 Which video series should you start with? 18:18 Setting up the code environment 19:45 Cloning the GitHub repository 20:40 Installing the dependencies with pip or uv 27:19 Running the code in JupyterLab 28:34 Troubleshooting Python environments 30:33 Checking CUDA and Apple Silicon support 32:43 Do you need a GPU? 34:30 Using a remote GPU with VS Code 39:35 Fixing CUDA and PyTorch issues 41:50 Questions and what comes next