Running Featured 1.25k FineWeb: decanting the web for the finest text data at scale đˇ 1.25k Generate high-quality text data for LLMs using FineWeb
Running 215 FineVision: Open Data is All You Need đ 215 A new open-source dataset for training VLMs
Running on CPU Upgrade Featured 2.81k The Smol Training Playbook đ 2.81k The secrets to building world-class LLMs
Running Featured 95 FunctionGemma Physics Playground đš 95 Use natural language to solve fun physics simulation puzzles
Running Featured 44 Porting nanochat to Transformers: an AI modeling history lesson đ 44 Learn about ML and Transformers through nanochat
Running 98 The Eiffel Tower Llama đ 98 Explore the Eiffel Tower Llama experiment with open-source models
Running 76 Unlocking On-Policy Distillation for Any Model Family đ 76 Apply on-policy distillation to any model family