Running 3.63k The Ultra-Scale Playbook π 3.63k The ultimate guide to training LLM on large GPU Clusters
meta-llama/Llama-3.1-8B-Instruct Text Generation β’ 8B β’ Updated Sep 25, 2024 β’ 12.2M β’ β’ 5.23k
meta-llama/Meta-Llama-3-8B-Instruct Text Generation β’ 8B β’ Updated Jun 18, 2025 β’ 1.53M β’ β’ 4.35k