Reasoning Models — The Video Signal

Build A Reasoning Model From Scratch 6: Reinforcement Learning 1 (Implementing GRPO for RLVR)

This session details implementing Reinforcement Learning with Verifiable Rewards (RLVR) using the GRPO algorithm to train a reasoning model. The process involves calculating rewards, advantages, and policy gradient loss to enhance reasoning capability.

Read article

Sebastian Raschka

Build A Reasoning Model Scratch 2: Loading a Base Model, Text Generation, and KV Caching

This guide details loading pre-trained LLMs (like Qwen3) and optimizing text generation through tokenization, KV caching, and torch.compile. Learn how to achieve high tokens/second throughput for reasoning models.

Read article

Sebastian Raschka

Build A Reasoning Model Scratch 1: Motivation & Code Setup

Learn how to build reasoning models from scratch, tracing the evolution from conventional LLMs to agent harnesses. The video covers setup using 'uv' and PyTorch best practices.

Read article