Aria is a multimodal foundation model developed by Rhymes AI. It processes both text and image inputs within a unified transformer architecture. The model is designed for versatile vision-language tasks and is distributed openly on Hugging Face for local use with the Transformers library.
In the Foundation models & chat space, Aria takes a focused approach. It focuses on understanding and reasoning over both text and images in a single model. It is built as an open-source project for developers. Aria is open source under the Apache-2.0 license. It ships for the web, the command line, and API.
rhymes-ai builds and maintains Aria, and it first shipped in 2024. The project is developed in the open on GitHub with 1.1k stars.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match