Gemma 

Gemma is a family of lightweight, open-source, large language models (LLMs) developed by Google DeepMind. Built on the same technology as Google\’s Gemini models, Gemma models are designed to be accessible, flexible, and suitable for a wide range of tasks, including question answering, summarization, and code generation. Its open weights allow developers and researchers to fine-tune the models for specific applications, deploy them on their own hardware or cloud services, and foster innovation.