LLMs from Scratch – Practical Engineering from Base Model to PPO RLHF

Learn to build a complete large language model from scratch using only pure PyTorch. This course takes you through the entire lifecycle, from foundational concepts to advanced alignment techniques. By the end, you'll have the deep, hands-on experience needed to build and customize your own LLMs. ✏️ Course developed by Vivek Kalyanarangan. 💻 Code: https://github.com/vivekkalyanarangan30/llm_from_scratch ❤️ Support for this channel comes from our friends at Scrimba – the coding platform that's reinvented interactive learning: https://scrimba.com/freecodecamp ⭐️ Contents ⭐️ 0:00:00 Part 0 - Introduction 0:05:43 Part 1 - Core Transformer Architecture 0:40:24 Part 2 — Training a Tiny LLM 1:30:27 Part 3 — Modernizing the Architecture 2:33:53 Part 4 — Scaling Up 3:17:22 Part 5 — Mixture-of-Experts (MoE) 3:44:19 Part 6 — Supervised Fine-Tuning (SFT) 4:23:44 Part 7 — Reward Modeling 4:59:55 Part 8 — RLHF with PPO 🎉 Thanks to our Champion and Sponsor supporters: 👾 Drake Milly 👾 Ulises Moralez 👾 Goddard Tan 👾 David MG 👾 Matthew Springman 👾 Claudio 👾 Oscar R. 👾 jedi-or-sith 👾 Nattira Maneerat 👾 Justin Hual -- Learn to code for free and get a developer job: https://www.freecodecamp.org Read hundreds of articles on programming: https://freecodecamp.org/news