Gemma is Google’s latest family of four LLM models, built on Gemini. It is available in two sizes: 2B and 7B parameters, each offering base (pretrained) and prompt-tuned versions.
Where to use
Google Gemma can be run on various types of consumer hardware, even without quantization, and has a context length of 8K tokens.
Features
– Open-source large language models
- gemma-7b: Base 7B model.
- gemma-7b-it: Instruction fine-tuned version of the base 7B model.
- gemma-2b: Base 2B model.
- gemma-2b-it: Instruction fine-tuned version of the base 2B model
- Originates from Google Gemini research
- Supports diverse application uses
- Accessible for the broad developer community
Benefits
– Accessible to diverse applications, enhancing versatility
– Open-source nature encourages broad collaboration and innovation
– Supports English-language tasks with high proficiency.