Hibiki fr-en Collection Hibiki is a model for streaming speech translation , which can run on device! See https://github.com/kyutai-labs/hibiki. • 4 items • Updated 29 minutes ago • 6
Tulu 3 Models Collection All models released with Tulu 3 -- state of the art open post-training recipes. • 10 items • Updated 8 days ago • 86
TinySwallow Collection Compact Japanese models trained with "TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models" • 5 items • Updated 8 days ago • 12
YuE Collection YuE is a groundbreaking series of open-source foundation models designed for music generation, led by HKUST. • 7 items • Updated 8 days ago • 2
Qwen2.5-1M Collection The long-context version of Qwen2.5, supporting 1M-token context lengths • 2 items • Updated 11 days ago • 97
Qwen2.5-VL Collection Vision-language model series based on Qwen2.5 • 3 items • Updated 11 days ago • 322
SmolVLM 256M & 500M Collection Collection for models & demos for even smoller SmolVLM release • 12 items • Updated 14 days ago • 65
AceMath Collection We are releasing math instruction models, math reward models, general instruction models, all training datasets, and a math reward benchmark. • 11 items • Updated 20 days ago • 9
SwiftKV Models Collection SwiftKV reduces prefill compute by up to 50% by combining model rewiring and knowledge-preserving self-distillation. • 4 items • Updated 14 days ago • 5
Sana Collection ⚡️Sana: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer • 19 items • Updated 29 days ago • 87
Multimodal Models Collection Multimodal models with leading performance. • 17 items • Updated 20 days ago • 30