Sebastian Raschka releases 8-part video course on building reasoning models in PyTorch
AI researcher Sebastian Raschka has published an 11-hour, eight-video course accompanying his book 'Build Reasoning Model (From Scratch),' which teaches how to implement reasoning model techniques such as inference scaling, reinforcement learning, and distillation using PyTorch. The course builds on a pre-trained LLM and is positioned as a sequel to his earlier 'Coding LLMs from the Ground Up' course, though it can be watched independently.
GoKawiil's interpretation of the reporting above, not reported fact.
The release reflects growing interest in reasoning models, which Raschka notes now underpin nearly all current-generation LLMs through added post-training techniques. By teaching these concepts from scratch in code, the course could help developers and researchers demystify how reasoning capabilities are built into LLMs rather than treating them as a black box.
- The course spans 8 videos totaling roughly 11 hours and pairs with Raschka's book 'Build Reasoning Model (From Scratch).'
- It covers inference scaling, reinforcement learning with verifiable rewards, and distillation techniques implemented in PyTorch.
- Raschka describes reasoning models as an upgrade to conventional LLMs via added post-training, and notes they can serve as the core engine behind AI agents.
Build a Large Language Model (From Scratch) book — Written by the same author behind this reasoning-model course, this book walks through implementing LLMs from the ground up in PyTorch. It's a perfect companion for readers who want hands-on, code-first understanding of the concepts discussed in the article.
See Build a Large Language Model (From Scratch) book on Amazon → Affiliate link — we may earn a commission on purchases, at no extra cost to you. Product picked by AI based on this article; it is not a tested recommendation.Source: magazine.sebastianraschka.com — Sebastian Raschka, 2026-10-26
Published there as: “Sebastian Raschka's from-scratch video course on building reasoning models”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.