<ul><li>The Allen Institute for AI has released Molmo, a family of open-source language models that can process text and images.</li><li>The Molmo model series comprises four neural networks with different parameters ranging from 1 billion to 72 billion.</li><li>Molmo models offer multimodal processing capabilities, including object recognition, counting objects, describing images, and explaining data in charts.</li><li>Molmo achieved competitive scores in benchmark tests and the smallest model is compact enough to run on mobile devices.</li></ul>

Allen Institute for AI debuts new Molmo series of open-source multimodal models

Discover more