Devstral 2 Collection A couple of agentic LLMs for software engineering tasks, excelling at using tools to explore codebases, edit multiple files, and power SWE Agents. • 3 items • Updated Dec 9, 2025 • 44
MiniCPM4 Collection MiniCPM4: Ultra-Efficient LLMs on End Devices • 30 items • Updated 13 days ago • 84
Self-Hinting Language Models Enhance Reinforcement Learning Paper • 2602.03143 • Published 22 days ago • 29
SAGE Collection Self-Hinting Language Models Enhance Reinforcement Learning • 19 items • Updated 16 days ago • 2
Qwen3-MoE Collection Compressed Qwen3 MoE models with a reduced number of experts. See additional models at https://huggingface.co/bknyaz. • 9 items • Updated 13 days ago • 2
ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thought Paper • 2601.23184 • Published 25 days ago • 36
REAP the Experts: Why Pruning Prevails for One-Shot MoE compression Paper • 2510.13999 • Published Oct 15, 2025 • 14