Running Featured 1.21k FineWeb: decanting the web for the finest text data at scale π· 1.21k Generate high-quality text data for LLMs using FineWeb
Running 3.55k The Ultra-Scale Playbook π 3.55k The ultimate guide to training LLM on large GPU Clusters
Running on CPU Upgrade Featured 2.54k The Smol Training Playbook π 2.54k The secrets to building world-class LLMs
Running Featured 39 Porting nanochat to Transformers: an AI modeling history lesson π 39 Learn about ML and Transformers through nanochat
Running 158 Qwen2.5 VL 32B Instruct Demo π 158 Interact with Qwen2.5-VL-32B-Instruct for text and image/video responses
Sleeping 18 i18n Agent - Contribute in Just 5 Minutes π€ 18 Translate Hugging Face docs into multiple languages