UBTree: Parallel Tree Drafting via Unigram and Bigram Models for Speculative Decoding Paper • 2609.39972 • Published 23 days ago • 35
deepseek-ai/DeepSeek-V4.1-Flash-1017 Image-Text-to-Text • 763B • Updated 6 days ago • 51.9k • • 2.34k
Selecting Diverse SFT Traces Improves Post-RL Generalization Paper • 2609.33780 • Published 26 days ago • 38
Running 179 HF Viewer · Model Architecture Explorer 🟩 179 Interactive architecture graph for any HF model
DeepSeek Elastic Compute (DSec): A Sandbox Infrastructure for Effective Agentic Training at Scale Paper • 2609.22978 • Published Sep 19 • 4
XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B Image-Text-to-Text • 9B • Updated about 1 month ago • 25.9k • 666
Running 12 DiffusionGemma Free Decision Endpoint 🎯 12 Generate structured decisions from text or images with one API call