N-Gram House

Tag: top-p

Controlling Length and Structure in LLM Outputs: Practical Decoding Parameters

Controlling Length and Structure in LLM Outputs: Practical Decoding Parameters

Learn how to control LLM output length and structure using decoding parameters like temperature, top-k, top-p, and repetition penalties. Practical settings for real-world use cases.

Categories

  • Machine Learning (110)
  • History (50)
  • Business AI Strategy (38)
  • Software Development (29)
  • AI Security (24)

Recent Posts

Incident Response for AI-Introduced Defects and Vulnerabilities: A Practical Guide Jun, 3 2026
Incident Response for AI-Introduced Defects and Vulnerabilities: A Practical Guide
Tokenization in Generative AI: BPE, WordPiece, and Future Methods Explained Jul, 25 2026
Tokenization in Generative AI: BPE, WordPiece, and Future Methods Explained
Grounding Prompts in Generative AI: Citing Sources with Retrieval-Augmented Generation Jul, 20 2026
Grounding Prompts in Generative AI: Citing Sources with Retrieval-Augmented Generation
Measuring and Reporting LLM Spend: Dashboards and KPIs That Matter Jun, 22 2026
Measuring and Reporting LLM Spend: Dashboards and KPIs That Matter
Grammar-Constrained LLM Outputs: A Guide for Enterprise Applications Jun, 21 2026
Grammar-Constrained LLM Outputs: A Guide for Enterprise Applications

Menu

  • About
  • Terms of Service
  • Privacy Policy
  • CCPA
  • Contact

© 2026. All rights reserved.