jondurbin/airoboros-l2-13b-2.1

jondurbin/airoboros-l2-13b-2.1 is a 13 billion parameter Llama-2 instruction-tuned model developed by jondurbin, utilizing synthetic data generated by the Airoboros framework. This model features experimental support for roleplay-style instruction sets, detailed writing prompts, and next-chapter generation. It is specifically optimized for context-obedient question answering, agent/function calling, chain-of-thought reasoning, and reWOO-style execution planning, making it suitable for complex interactive AI applications.