Introducing Idefics2: A Powerful 8B Vision-Language Model for the community

Introducing IDEFICS: An Open Reproduction of State-of-the-art Visual Langage Model

A Dive into Vision-Language Models

SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data

Vision Language Model Alignment in TRL ⚡️

Introducing The World's Largest Open Multilingual Language Model: BLOOM

Introducing Gemma 3 270M: The compact model for hyper-efficient AI

Today, we're adding a new, highly specialized tool to the Gemma 3 toolkit: Gemma 3 270M, a compact, 270-million parameter model.