Apple Intelligence Foundation Language Models
arXiv:2407.21075 (arXiv), 2024
Abstract
We present foundation language models developed to power Apple Intelligence features, including a ~3 billion parameter model designed to run efficiently on devices and a large server-based language model designed for Private Cloud Compute. 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 the model development.
BibTeX
@article{gunter2024apple,
title={Apple Intelligence Foundation Language Models},
author={Gunter, Tom and Wang, Zirui and Wang, Chong and Pang, Ruoming and Narayanan, Andy and Zhang, Aonan and Zhang, Bowen and Chen, Chen and Chiu, Chung-Cheng and Qiu, David and others},
journal={arXiv preprint arXiv:2407.21075},
year={2024}
}