view article Article Nemotron 3 Nano \- A new Standard for Efficient, Open, and Intelligent Agentic Models Dec 15, 2025 • 108
Running Featured 1.29k FineWeb: decanting the web for the finest text data at scale 🍷 1.29k Download a trillion‑token web text dataset for LLM training
Running on CPU Upgrade Featured 2.98k The Smol Training Playbook 📚 2.98k The secrets to building world-class LLMs
Energy-Based Transformers are Scalable Learners and Thinkers Paper • 2507.02092 • Published Jul 2, 2025 • 69
Running 3.69k The Ultra-Scale Playbook 🌌 3.69k The ultimate guide to training LLM on large GPU Clusters