Apple has released eight open source large language models (LLMs) called OpenELM, designed to run on-device rather than through cloud servers. These models are available on the Hugging Face Hub and include code, training logs, and multiple versions, enabling researchers and developers to investigate and modify them for various applications.
Apple has released OpenELM, a set of four open-source language models aimed at running AI tasks efficiently on Apple devices. OpenELM stands for ‘Open-source Efficient Language Models’ and boasts smaller sizes than most lightweight AI models, enabling smooth operation on devices like phones and laptops. This release marks Apple’s continued focus on developing AI capabilities to run locally on Apple devices, aligning with CEO Tim Cook’s earlier hints about the company’s ambitions in generative AI.
