Introduction
Google’s Gemma is a family of lightweight, state-of-the-art open language models (LLMs) developed using the same research and technology as Google's Gemini models. It includes 2B and 7B parameter versions, with both base and instruction-tuned modifications. Gemma is designed with AI principles to ensure safe and reliable use, featuring cross-device compatibility and optimization for Google Cloud and NVIDIA GPUs. It is accessible for free on platforms like Kaggle and Colab, and through Google Cloud with Vertex AI or GKE.