view article Article Releasing the largest multilingual open pretraining dataset By Pclanglais • 14 days ago • 95
Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders Paper • 2410.22366 • Published about 1 month ago • 75
SmolLM2 Collection State-of-the-art compact LLMs for on-device applications: 1.7B, 360M, 135M • 15 items • Updated about 12 hours ago • 181
Pyramidal Flow Matching for Efficient Video Generative Modeling Paper • 2410.05954 • Published Oct 8 • 38