AI Radar

Phi-1.5

Available · Language

Phi-1.5 is a 1.3 billion parameter base language model from Microsoft, presented in a September 2023 technical report that applies the phi-1 textbook-data approach to common-sense reasoning in natural language. Microsoft open-sourced it for research on issues such as hallucination, toxicity and bias, with weights on Hugging Face under the MIT License. [1] [2] Primary source

Timeline of Phi-1.5 →

Claims and evidence

  • Announced Primary source[1]Submission history, v1
  • ReleasedRelease date unknown
  • Status AvailableWeights are still downloadable from Microsoft's Hugging Face organisation (checked 2026-10-01). Primary source[2]
  • Successor of Phi-1The report presents phi-1.5 as follow-up work on phi-1 with the same textbook-data approach; the card says it was trained on the phi-1 data sources plus new synthetic NLP texts. Primary source[1]abstract [2]Model Summary
  • Change · Training data Adds a new source of synthetic NLP texts to the phi-1 data sources, moving the focus from Python coding to common-sense reasoning in natural language.Compared with Phi-1 Primary source[2] [1]
  • Change · Other The model card lists question-answer, chat and code prompt formats, whereas phi-1 was specialised for basic Python coding.Compared with Phi-1 Primary source[2] [3]
  • Input text Primary source[2]Intended Uses
  • Output text Primary source[2]Intended Uses
  • Open weights Yes Primary source[2]License
  • Parameters 1.3 billion Primary source[1]abstract [2]Model Summary
  • Access Open-weights download Primary source[2]

Lineage

Predecessors

Successors

  • Phi-2 · 12 December 2023

Based on

Not derived from another model.

Variants and derived

None recorded.

Siblings

None recorded.

All ancestors

All descendants

Variants

No variants recorded in this record.

Related AI Radar coverage

AI Radar coverage starts in June 2026; no coverage linked yet.

All model releases from Microsoft on AI Radar →