view article Article SmolVLM Grows Smaller – Introducing the 250M & 500M Models! By andito and 2 others • Jan 23 • 180
Sana Collection ⚡️Sana: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer • 21 items • Updated Apr 17 • 92
SmolLM2 Collection State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 16 items • Updated May 5 • 266
LLaVA-OneVision Collection a model good at arbitrary types of visual input • 15 items • Updated Oct 5, 2024 • 24