Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance Paper • 2511.13254 • Published 2 days ago • 84
MXFP4 Hybrid GGUF Collection MXFP4 hybrid GGUF models getting... well.. Getting some interesting results. • 11 items • Updated 2 days ago • 2
RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation Paper • 2509.16198 • Published Sep 19 • 127
DiffusionNFT: Online Diffusion Reinforcement with Forward Process Paper • 2509.16117 • Published Sep 19 • 21
FastVLM Collection Efficient Vision Encoding for Vision Language Models • 9 items • Updated Sep 2 • 103
Jamba 1.7 Collection The AI21 Jamba family of models are hybrid SSM-Transformer foundation models, blending speed, efficient long context processing, and accuracy. • 4 items • Updated Jul 2 • 12
view article Article Bringing the Artificial Analysis LLM Performance Leaderboard to Hugging Face May 3, 2024 • 14
Radial Attention: O(nlog n) Sparse Attention with Energy Decay for Long Video Generation Paper • 2506.19852 • Published Jun 24 • 41
Align Your Flow: Scaling Continuous-Time Flow Map Distillation Paper • 2506.14603 • Published Jun 17 • 19