Building a Reasoning Model from Scratch
How to teach a small language model to think step-by-step using reinforcement learning with verifiable rewards -- from SFT on chain-of-thought data to GRPO training to distillation.
intermediate~3 hours4 notebooksReasoning ModelsChain-of-ThoughtSupervised Fine-TuningGRPOVerifiable RewardsRejection SamplingDistillationDeepSeek-R1
Curator of this Module
Dr. Rajat Dandekar
Course Instructor
Dr. Rajat Dandekar is a researcher and educator specializing in AI/ML, with a passion for making complex concepts accessible through intuitive explanations and hands-on learning.
Checking access…
Learning Path
Article
1
Notebook 12
Notebook 23
Notebook 34
Notebook 4Case Study
Certificate