Gemma 3 QAT Collection Quantization Aware Trained (QAT) Gemma 3 checkpoints. The model preserves similar quality as half precision while using 3x less memory • 15 items • Updated 19 days ago • 186
Running 2.56k 2.56k The Ultra-Scale Playbook 🌌 The ultimate guide to training LLM on large GPU Clusters
xLAM: A Family of Large Action Models to Empower AI Agent Systems Paper • 2409.03215 • Published Sep 5, 2024 • 4
Running 934 934 FineWeb: decanting the web for the finest text data at scale 🍷 Generate high-quality web text data for LLM training
Running on CPU Upgrade 13k 13k Open LLM Leaderboard 🏆 Track, rank and evaluate open LLMs and chatbots