15 · Math for LLMs

This chapter contains the following subtopics:

• 01 · Tokenization Math
• 02 · Embedding Space Math
• 03 · Attention Mechanism Math
• 04 · Positional Encodings
• 05 · Language Model Probability
• 06 · Training at Scale
• 07 · Fine Tuning Math
• 08 · Scaling Laws
• 09 · Efficient Attention and Inference
• 10 · Mixture of Experts and Routing
• 11 · Quantization and Distillation
• 12 · RAG Math and Retrieval
• 13 · Serving and Systems Tradeoffs