Running 31 Weight-Space Geometry of Offline Reasoning Training 🧭 31 Interactive weight-space geometry of six reasoning losses
Runtime error Agents 13 Hermes · SIQ-1-35B (ZeroGPU) 🪽 13 Create web apps and see live preview instantly
view article Article Borealis — open data, code, weights recipe for training Audio LLM AlexWortega • May 25 • 17
Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation Paper • 2601.22813 • Published Jan 30 • 63
view article Article Introducing smolagents: simple agents that write actions in code. +1 m-ric, merve, thomwolf • Dec 31, 2024 • 1.21k
Quartet: Native FP4 Training Can Be Optimal for Large Language Models Paper • 2505.14669 • Published May 20, 2025 • 79