Running 2.28k 2.28k The Ultra-Scale Playbook 🌌 The ultimate guide to training LLM on large GPU Clusters
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention Paper • 2502.11089 • Published 30 days ago • 144
BenchMAX: A Comprehensive Multilingual Evaluation Suite for Large Language Models Paper • 2502.07346 • Published Feb 11 • 51
Expect the Unexpected: FailSafe Long Context QA for Finance Paper • 2502.06329 • Published Feb 10 • 126
Teaching Language Models to Critique via Reinforcement Learning Paper • 2502.03492 • Published Feb 5 • 24
Scaling Pre-training to One Hundred Billion Data for Vision Language Models Paper • 2502.07617 • Published Feb 11 • 29
SynthDetoxM: Modern LLMs are Few-Shot Parallel Detoxification Data Annotators Paper • 2502.06394 • Published Feb 10 • 86