Running on CPU Upgrade 13.4k 13.4k Open LLM Leaderboard π Track, rank and evaluate open LLMs and chatbots
Running 122 122 Open-LLM performances are plateauing, letβs make the leaderboard steep again π Update leaderboard for fair model evaluation
meta-llama/Llama-3.1-405B-Instruct-FP8 Text Generation β’ 406B β’ Updated Sep 25, 2024 β’ 6.55k β’ 188
unsloth/Meta-Llama-3.1-405B-Instruct-bnb-4bit Text Generation β’ 211B β’ Updated Sep 11, 2024 β’ 778 β’ 6