Running on CPU Upgrade Featured 3.07k The Smol Training Playbook π 3.07k The secrets to building world-class LLMs
Running 79 Maintain the unmaintainable π 79 Explore the complex relationships between 400+ machine learning models
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B Text Generation β’ 8B β’ Updated Feb 24, 2025 β’ 619k β’ β’ 799
meta-llama/Llama-3.1-8B-Instruct Text Generation β’ 8B β’ Updated Sep 25, 2024 β’ 8.34M β’ β’ 5.64k
mattshumer/Reflection-Llama-3.1-70B Text Generation β’ 71B β’ Updated Sep 24, 2024 β’ 303 β’ 1.71k
Running Featured 127 Open-LLM performances are plateauing, letβs make the leaderboard steep again π 127 Explore and compare advanced language models on a new leaderboard
Running Featured 1.32k FineWeb: decanting the web for the finest text data at scale π· 1.32k Read a detailed overview of the FineWeb webβscale text dataset