Skip to main content
GGenerative AI
    • Start here
    • Learning paths5 paths
    • Modules11 modules
    • Projects5 projects
    • Quizzes
    • Flashcards
    • Homework
    • Interview prep8 question banks
    • Cheat sheets11 sheets
    • Glossary239 terms
    • Code snippets
    • Ask the mentor
    • My notes
    • My progress
SearchStart here
Menu
    • Start here
    • Learning paths5 paths
    • Modules11 modules
    • Projects5 projects
    • Quizzes
    • Flashcards
    • Homework
    • Interview prep8 question banks
    • Cheat sheets11 sheets
    • Glossary239 terms
    • Code snippets
    • Ask the mentor
    • My notes
    • My progress
  1. Reference
  2. Top-p (nucleus sampling)

Glossary

Top-p (nucleus sampling)

A sampling filter that keeps the smallest set of tokens whose cumulative probability reaches p. It keeps few tokens when the model is confident and more when it is unsure.

Where it is explained

  • Sampling parameters and the model landscapeLLM foundations

See also

Terms explained in the same lessons.

  • API-only model
  • Batch invariance
  • Context window
  • Greedy decoding
  • Open-weight model
  • Sampling
Previous termTop-kNext termTrace

All terms, A to Z

GGenerative AI

Learn generative AI from the first token to production systems.

  • Privacy
  • Search