Running Featured 1.46k FineWeb: decanting the web for the finest text data at scale ๐ท 1.46k Explore the FineWeb dataset and its creation process
Running on CPU Upgrade Featured 3.35k The Smol Training Playbook ๐ 3.35k The secrets to building world-class LLMs
Running 4.11k The Ultra-Scale Playbook ๐ 4.11k The ultimate guide to training LLM on large GPU Clusters