Modern LLMs
Architecture, training, inference, agents, and evaluation of modern language-model systems.
Contents
- Module 1. The Modern LLM Landscape · Quizzes · Exercises · Notebooks
- Module 2. Tokenization and Embeddings · Quizzes · Exercises · Notebooks
- Module 3. The Basic Transformer · Quizzes · Exercises · Notebooks
- Module 4. Positional representations: from sinusoids to multiple axes · Quizzes · Exercises · Notebooks
- Module 5. Modern Attention Mechanisms · Quizzes · Exercises · Notebooks
- Module 6. Normalization, activations, and the anatomy of a Transformer block · Quizzes · Exercises · Notebooks
- Module 7. Mixture of Experts · Quizzes · Exercises · Notebooks
- Module 8. Beyond the Transformer: SSMs, Mamba, and Hybrid Sequence Models · Quizzes · Exercises · Notebooks
- Module 9. Pretraining: Data, Scaling Laws, and Optimizers · Quizzes · Exercises · Notebooks
- Module 10. KV Caches and Efficient Inference · Quizzes · Exercises · Notebooks
- Module 11. Speculative Decoding and Quantization · Quizzes · Exercises · Notebooks
- Module 12. Diffusion Language Models · Quizzes · Exercises · Notebooks
- Module 13. Supervised Fine-Tuning and Data Work · Quizzes · Exercises · Notebooks
- Module 14. Learning from Feedback: RLHF, DPO, RLOO, and GRPO · Quizzes · Exercises · Notebooks
- Module 15. Reasoning Models and Test-Time Compute · Quizzes · Exercises · Notebooks
- Module 16. Multimodal LLMs: Vision, Audio, and Video · Quizzes · Exercises · Notebooks
- Module 17. Embeddings, Retrieval, and RAG · Quizzes · Exercises · Notebooks
- Module 18. Agents and Tool Use · Quizzes · Exercises · Notebooks
- Module 19. Evaluating Modern LLM Systems: From Benchmarks to Decisions · Quizzes · Exercises · Notebooks
- Module 20. The complete LLM: from tokens to training and generation · Quizzes · Exercises · Notebooks