Running 3.04k 3.04k The Ultra-Scale Playbook π The ultimate guide to training LLM on large GPU Clusters
Running 68 68 Scaling FineWeb to 1000+ languages: Step 1: finding signal in 100s of evaluation tasks π Evaluate multilingual models using FineTasks
Running 116 116 TxT360: Trillion Extracted Text π Create a large-scale deduplicated text dataset for LLM training
Running 1.03k 1.03k FineWeb: decanting the web for the finest text data at scale π· Generate high-quality web text data for LLM training
mistralai/Mistral-7B-Instruct-v0.2 Text Generation β’ 7B β’ Updated 21 days ago β’ 938k β’ β’ 2.91k