Phi
Microsoft's small models trained mainly on curated textbook-quality data.
Overview
Phi is a family of small language models trained on a deliberately narrow, high-quality corpus of textbooks and exercises rather than on a web-scale crawl. It solves the assumption that capability requires scale, showing that data selection can substitute for a large part of it. It exists because it reframes the question from how much data to what kind of data, and the answer is useful when the budget is a single GPU.
Technology Graph
How Phi connects to the rest of the stack.
Uses and depends on
- Transformer architecture Algorithms Phi based on Transformer High ✓ source
Tools
Software that implements or integrates with Phi.
Infrastructure
Alternatives
Comparisons
Side-by-side breakdowns with the alternatives above.