Running Featured 1.35k FineWeb: decanting the web for the finest text data at scale π· 1.35k Explore and download the FineWeb webβscale text dataset
Running on CPU Upgrade Featured 3.19k The Smol Training Playbook π 3.19k The secrets to building world-class LLMs
deepseek-ai/DeepSeek-V3.2-Speciale Text Generation β’ 685B β’ Updated Dec 1, 2025 β’ 14.8k β’ β’ 706
nvidia/Llama-3_1-Nemotron-Ultra-253B-v1 Text Generation β’ 253B β’ Updated Oct 15, 2025 β’ 3.52k β’ β’ 348