Sebastian Raschka releases 11 hours of free lectures on building reasoning models from scratch

Sebastian Raschka's from-scratch video course on building reasoning models

Sebastian Raschka has recorded eight coding lectures (about 11 hours) to accompany his book Build a Reasoning Model (From Scratch). Starting from a pre-trained Qwen3 0.6B model, the course implements evaluation, inference-time scaling, reinforcement learning with verifiable rewards, and distillation in Python and PyTorch. A math-answer verifier built early on later doubles as the reward signal for GRPO training. Python and PyTorch familiarity is recommended; early examples run on CPU, while training is far more practical on a GPU.