Running on CPU Upgrade Featured 3.11k The Smol Training Playbook π 3.11k The secrets to building world-class LLMs
deepseek-ai/DeepSeek-R1-0528-Qwen3-8B Text Generation β’ 8B β’ Updated May 29, 2025 β’ 302k β’ β’ 1.05k
Running 596 Scaling test-time compute π 596 Run advanced search strategies to boost LLM problem solving
CohereLabsCommunity/multilingual-reward-bench Viewer β’ Updated Jul 23, 2025 β’ 66.8k β’ 486 β’ 34
Running Featured 1.33k FineWeb: decanting the web for the finest text data at scale π· 1.33k Explore and download the FineWeb webβtext dataset