Build a reasoning model from scratch
-
Chapter 63. Understanding reasoning models
-
Chapter 64. Generating text with a pre-trained LLM
-
Chapter 65. Evaluating reasoning models
-
Chapter 66. Improving reasoning with inference-time scaling
-
Chapter 67. Inference-time Scaling via Self-Refinement
-
Chapter 68. Training reasoning models with reinforcement learning
-
Chapter 69. Improving GRPO for reinforcement learning
-
Chapter 70. Distilling reasoning models for efficient reasoning
-
Chapter 71. References and further reading
-
Chapter 72. Exercise solutions
-
Chapter 73. Qwen3 LLM source code
-
Chapter 74. Common approaches to model evaluation