The Smol Training Playbook
📚
3.25k
The secrets to building world-class LLMs
Training-LLMs
-
-
The Ultra-Scale Playbook
🌌3.95kThe ultimate guide to training LLM on large GPU Clusters
-
FineWeb: decanting the web for the finest text data at scale
🍷1.4kExplore and download the FineWeb web‑scale text dataset
-
FineVision: Open Data is All You Need
📝232A new open-source dataset for training VLMs