LLM Essentials in Large Language Models

Lessons in this section

1. LLM Basics

   What a large language model is, the one job it does (guess the next word), what it is good at, what it cannot do, and how it learned from text.

2. Generation Flow

   The full path from the prompt you type to the reply you read: chat messages, tokens, the model, picking a token, the loop, stopping, and streaming.

3. Model Limits

   The real limits of an LLM: the context window, output length, knowledge cutoff, model size and memory, speed, and cost, with small calculations for each.