We present foundation language models developed to power Apple Intelligence features, including a roughly 3 billion parameter model designed to run efficiently on devices and a large server-based language model designed for private cloud computing. These models are designed to perform a wide range of tasks efficiently, accurately, and responsibly. This report describes the model architecture, the data used to train the model, the training process, how the models are optimized for inference, and the evaluation results. We highlight our focus on responsible ai and how the principles are applied throughout model development.
This document provides technical details for Apple's server and device base models introduced on June 10, 2024 in this publication.
