view article Article Apriel-1.6-15b-Thinker: Cost-efficient Frontier Multimodal Performance 8 days ago • 74
view article Article Apriel-1.6-15b-Thinker: Cost-efficient Frontier Multimodal Performance 8 days ago • 74
DNA Bench: When Silence is Smarter -- Benchmarking Over-Reasoning in Reasoning LLMs Paper • 2503.15793 • Published Mar 20
SYNTHETIC-1 Collection A collection of tasks & verifiers for reasoning datasets • 9 items • Updated Oct 7 • 67
Running 3.58k The Ultra-Scale Playbook 🌌 3.58k The ultimate guide to training LLM on large GPU Clusters