Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4 model family and supports 128K token context length. The model underwent an enhancement process, incorporating both supervised fine-tuning and direct preference optimization to support precise instruction adherence and robust safety measures.

Phi-4-mini-instruct is a dense decoder-only Transformer model with 3.8B parameters, offering key improvements over Phi-3.5-Mini, including a 200K vocabulary, grouped-query attention, and shared embedding. It is designed for chat-completion prompts, generating text based on user input, with a context length of 128K tokens. This static model was trained on an offline dataset with a June 2024 data cutoff. It supports many languages, including Arabic, Chinese, Czech, Danish, Dutch, English, Finnish, French, German, Hebrew, Hungarian, Italian, Japanese, Korean, Norwegian, Polish, Portuguese, Russian, Spanish, Swedish, Thai, Turkish, Ukrainian.

The model is intended for broad multilingual commercial and research use. The model provides uses for general purpose AI systems and applications which require 1) memory/compute constrained environments; 2) latency bound scenarios; 3) strong reasoning (especially math and logic). The model is designed to accelerate research on language and multimodal models, for use as a building block for generative AI powered features.