MOSS-Audio Collection An open-source audio understanding model supporting speech recognition, environmental sound analysis, music understanding, time-aware QA, and complex • 7 items • Updated May 2 • 66
DiffusionBlocks: Blockwise Training for Generative Models via Score-Based Diffusion Paper • 2506.14202 • Published Jun 17, 2025 • 4
SWE-rebench-V2 Collection SWE-rebench-V2 is a curated dataset of software-engineering tasks derived from real GitHub issues and pull requests. • 3 items • Updated Mar 3 • 18
MiniCPM5 Collection A SOTA 1B on-device LLM, small yet powerful. • 11 items • Updated 13 days ago • 26
Nemotron-Labs-Diffusion Collection A Tri-Mode Language Model Family Unifying Autoregressive, Diffusion, and Self-Speculation Decoding • 7 items • Updated 24 minutes ago • 48
Anima Preview 3 SDNQ Checkpoints Collection SDNQ Anima Preview 3 component and full Diffusers checkpoints with 1024 benchmark grids. • 4 items • Updated 25 days ago • 1
HiDream O1 Image SDNQ 4-bit Quantization Variants Collection Fixed SDNQ 4-bit HiDream O1 base variants with BF16 pairwise demos and speed/VRAM/storage tables. • 5 items • Updated 28 days ago • 1
HiDream-O1-Image-Dev SDNQ 4-bit Quantization Variants Collection Fixed SDNQ 4-bit HiDream O1 variants with BF16 pairwise demos and speed/VRAM/storage tables. • 5 items • Updated 28 days ago • 1
ERNIE-Image Collection The serieas of image generation models, including text2img、img2img. • 4 items • Updated 18 days ago • 25