NousResearch/DeepHermes-3-Llama-3-3B-Preview

DeepHermes 3 - Llama-3 3B Preview by Nous Research is a 3.2 billion parameter language model with a 32768 token context length. It uniquely unifies intuitive and long chain-of-thought reasoning modes, toggled by a system prompt, making it one of the first models to integrate these distinct response styles. This model is designed for advanced reasoning tasks, improved LLM annotation, judgment, and function calling, offering enhanced steerability and control for users.