Llama

Llama: An open-source large language model (LLM) developed by Meta.

Llama 2: An updated version, freely available for research and commercial purposes. Uses transformer architecture like GPT-3 but is optimized for specific tasks.

Llama 2 (meta.com)

Code Llama: A specialized version of Llama 2 focused on code generation. It’s trained on 500 billion tokens of code and supports languages like Python, C++, Java, PHP, Typescript, C#, and Bash.

Code Llama, a state-of-the-art large language model for coding (meta.com)