Running Featured 74 QED-Nano: Teaching a Tiny Model to Prove Hard Theorems π 74 Who needs 1T parameters? Olympiad proofs with a 4B model
Running 80 Maintain the unmaintainable π 80 Explore the complex relationships between 400+ machine learning models
Running 224 FineVision: Open Data is All You Need π 224 A new open-source dataset for training VLMs
Running 92 Scaling FineWeb to 1000+ languages: Step 1: finding signal in 100s of evaluation tasks π 92 Evaluate multilingual models using FineTasks
Running on CPU Upgrade 232 The Synthetic Data Playbook: Generating Trillions of the Finest Tokens π 232 Explore synthetic data experiments on a virtual bookshelf
Running on CPU Upgrade Featured 3.15k The Smol Training Playbook π 3.15k The secrets to building world-class LLMs
Running 3.83k The Ultra-Scale Playbook π 3.83k The ultimate guide to training LLM on large GPU Clusters
Runtime error Agents Featured 2.77k XTTS πΈ 2.77k Generate speech from text using a reference voice
Running 596 Scaling test-time compute π 596 Run advanced search strategies to boost LLM problem solving
Running Featured 1.34k FineWeb: decanting the web for the finest text data at scale π· 1.34k Explore and download the FineWeb webβtext dataset