Running 4.06k The Ultra-Scale Playbook π 4.06k The ultimate guide to training LLM on large GPU Clusters
Running 602 Scaling test-time compute π 602 Boost LLM answers with flexible testβtime search strategies
meta-llama/Llama-3.2-3B-Instruct Text Generation β’ 3B β’ Updated Oct 24, 2024 β’ 1.57M β’ β’ 2.71k
human-centered-summarization/financial-summarization-pegasus Summarization β’ 0.6B β’ Updated Apr 26, 2024 β’ 3.11k β’ β’ 155
Salesforce/blip-image-captioning-large Image-to-Text β’ 0.5B β’ Updated Feb 3, 2025 β’ 583k β’ 1.49k