QuestionQ200

Fundamentals of GenAI

Which large language model (LLM) parameter determines the number of possible next words or tokens considered at each step in the text-generation process?

  • A Maximum tokens
  • B Top K
  • C Temperature
  • D Batch size
Explanation

Top K sampling restricts each generation step to the K most likely next tokens, thereby controlling how many candidate tokens are considered. Maximum tokens controls response length, temperature controls sampling randomness, and batch size controls how many inputs are processed together.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!