Language models have been effective in a wide range of applications, yet the most sophisticated models are often proprietary. For example, GPT-4 by OpenAI and various models by Anthropic are expensive and consume substantial energy. In contrast, the open-source community has produced competitive models, like Llama3. Furthermore, niche-specific smaller language models, such as those tailored for legal, medical or financial tasks, have outperformed their proprietary counterparts. This paper introduces a novel approach that employs \textit{functional tokens} to integrate \textbf{multiple open-source models}, each optimized for particular tasks. Our newly developed Octopus v4 model leverages \textit{functional tokens} to intelligently direct user queries to the most appropriate vertical model and reformat the query to achieve the best performance. Octopus v4, an evolution of the Octopus v1, v2, and v3 models, excels in selection and parameter understanding and reformatting. Additionally, we explore the use of graph as a versatile data structure that effectively coordinates multiple open-source models by harnessing the capabilities of the Octopus model and \textit{functional tokens}. Use our open-sourced GitHub (\url{https://www.nexa4ai.com/}) to try Octopus v4 models (\url{https://huggingface.co/NexaAIDev/Octopus-v4}), and contrite to a larger graph of language models. By activating models less than 10B parameters, we achieved SOTA MMLU score of 74.8 among the same level models.

翻译：语言模型在众多应用中已展现出卓越效果，然而最先进的模型往往具有专有性。例如OpenAI的GPT-4及Anthropic的多款模型不仅使用成本高昂，且消耗大量能源。相比之下，开源社区已开发出具有竞争力的模型（如Llama3）。此外，针对法律、医疗或金融等特定领域的专业化小型语言模型，其性能已超越专有模型。本文提出一种创新方法，采用**功能标记（functional tokens）** 整合**多个开源模型**，每个模型针对特定任务进行优化。新开发的Octopus v4模型利用功能标记智能地将用户查询导向最合适的垂直模型，并重新格式化查询以获取最优性能。作为Octopus v1、v2及v3模型的演进版本，Octopus v4在模型选择、参数理解与查询重格式化方面表现卓越。同时，我们探索将图（graph）作为通用数据结构，通过结合Octopus模型与功能标记的能力高效协调多个开源模型。可通过我们开源的GitHub项目（\url{https://www.nexa4ai.com/}）体验Octopus v4模型（\url{https://huggingface.co/NexaAIDev/Octopus-v4}），并共同构建更庞大的语言模型图。通过激活参数不足100亿的模型，我们在同级别模型中实现了74.8的SOTA MMLU分数。