view article Article Efficient LLM Pretraining: Packed Sequences and Masked Attention By sirluk • Oct 7, 2024 • 39
Running 2.62k 2.62k The Ultra-Scale Playbook 🌌 The ultimate guide to training LLM on large GPU Clusters
ModernBERT Collection Bringing BERT into modernity via both architecture changes and scaling • 3 items • Updated Dec 19, 2024 • 141
Running 950 950 FineWeb: decanting the web for the finest text data at scale 🍷 Generate high-quality web text data for LLM training