Sebastian Raschka released an eight-video, 11-hour course on building reasoning models from scratch in PyTorch, covering inference scaling, reinforcement learning, and distillation1. The course starts from a pre-trained LLM and implements evaluation and improvement methods, serving as a sequel to Raschka's earlier Coding LLMs from the Ground Up series.
Raschka Publishes 11-Hour Reasoning Model Course in PyTorch
Sebastian Raschka released an eight-video, 11-hour course covering how to build reasoning models from scratch in PyTorch, including reinforcement…
Was this useful?
The day’s vector, in your inbox.
Vector Wire Daily: one dispatch each publishing day.