# Multi-scale Parameters

ShieldGemma is a series of safety content moderation models based on Gemma 2, designed to moderate content across four harm categories (sexual content, dangerous content, hate speech, and harassment).

OpenELM is a set of open, efficient language models that employ a hierarchical scaling strategy to optimize parameter allocation and improve model accuracy. It offers pretrained and instruction-tuned versions ranging from 270 million to 3 billion parameters.