From the source
SmolVLA is a compact (450M) open-source Vision-Language-Action model for robotics, trained on community data, that outperforms larger models on simulation and real-world tasks.
SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data
Story of the weekNew model
From the source
Today, we introduce SmolVLA, a compact (450M), open-source Vision-Language-Action model for robotics that runs on consumer hardware.
huggingface.co
