NousResearch/Hermes-2-Pro-Llama-3-8B

Hermes 2 Pro - Llama-3 8B is an 8 billion parameter language model developed by Nous Research, @interstellarninja, and Fireworks.AI. It is an upgraded, retrained version of Nous Hermes 2, built on the Llama-3 architecture. This model excels in general task and conversation capabilities, with a strong focus on Function Calling, JSON Structured Outputs, and agentic capabilities, scoring 90% on function calling and 84% on structured JSON output evaluations.