Learn Large Language Models (LLMs)

Understand how language models learn, generate, and get evaluated.

Start learning 6 lessons · about 1 hours · free
About this track

Build a practical mental model of large language models: tokens and next-token prediction, Transformer attention, training and adaptation, prompting, inference controls, evaluation, and responsible use.

Before you start
  • No prior LLM experience needed.
  • Basic programming concepts are helpful but not required.
  • A modern browser with JavaScript enabled.
  1. Unit 1 · 0/2 lessons

    LLM foundations

    Learn token prediction and the Transformer architecture. Badge: Context reader

    1. 0x001Understand tokens and next-token predictionSee how text becomes model input and how a language model generates a sequence. 12 min 12 min
    2. 0x102Explore Transformers and attentionLearn how attention lets token representations use information from surrounding context. 12 min 12 min
  2. Unit 2 · 0/3 lessons

    Training and using LLMs

    Explore model adaptation, prompts, and inference behavior. Badge: Model guide

    1. 0x203Trace pretraining and model adaptationSeparate broad language-model pretraining from later task and behavior adaptation. 12 min 12 min
    2. 0x304Shape prompts and manage contextGive a model a clear task, useful context, and constraints for its response. 12 min 12 min
    3. 0x405Understand inference and generation controlsSee how decoding choices affect variation, length, and practical limits. 12 min 12 min
  3. Unit 3 · 0/1 lessons

    Evaluation and responsible use

    Test model quality, limitations, and safeguards. Badge: Careful evaluator

    1. 0x506Evaluate LLMs and use them responsiblyTest behavior on realistic cases and plan for errors, privacy, and human oversight. 12 min 12 min
Gostou da aula? 😆👍
Apoie nosso trabalho com uma doação:
Quero contribuir