Running 109 109 TxT360: Trillion Extracted Text ๐ Create a large, deduplicated dataset for LLM pre-training
Running 2.48k 2.48k The Ultra-Scale Playbook ๐ The ultimate guide to training LLM on large GPU Clusters
Running 109 109 TxT360: Trillion Extracted Text ๐ Create a large, deduplicated dataset for LLM pre-training
Running 62 62 Scaling FineWeb to 1000+ languages: Step 1: finding signal in 100s of evaluation tasks ๐ Evaluate multilingual models using FineTasks
Running 917 917 FineWeb: decanting the web for the finest text data at scale ๐ท Generate high-quality web text data for LLM training
Power Scheduler: A Batch Size and Token Number Agnostic Learning Rate Scheduler Paper โข 2408.13359 โข Published Aug 23, 2024 โข 25
Neural Circuit Diagrams: Robust Diagrams for the Communication, Implementation, and Analysis of Deep Learning Architectures Paper โข 2402.05424 โข Published Feb 8, 2024 โข 16