1
Phi-4 is a state-of-the-art open model trained on high-quality synthetic, public, and academic data for advanced reasoning. It uses fine-tuning and preference optimization for precise instruction adherence and safety.
  • ID
    phi-4
  • Type
    text-to-text
  • Updated
    Jul 07, 2025
  • Input
  • Output
  • Config
  • Privacy
    Public
  • License
  • Toolkit
  • Use Case
  • Share
    • Badge
      phi-4
    OSZAR »