Running Featured 1.33k FineWeb: decanting the web for the finest text data at scale π· 1.33k Read a detailed overview of the FineWeb webβscale text dataset
Running on CPU Upgrade Featured 3.11k The Smol Training Playbook π 3.11k The secrets to building world-class LLMs
nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 Text Generation β’ Updated Oct 15, 2025 β’ 6.89k β’ β’ 345
meta-llama/Llama-4-Scout-17B-16E-Instruct Image-Text-to-Text β’ Updated May 22, 2025 β’ 367k β’ β’ 1.27k