Running 2.8k 2.8k The Ultra-Scale Playbook π The ultimate guide to training LLM on large GPU Clusters
Running 67 67 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, deduplicated dataset for LLM pre-training
Running 995 995 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 Sep 27, 2024 β’ 1.68M β’ β’ 2.86k