章鱼 v4：语言模型图

Octopus v4: Graph of language models

April 30, 2024

作者: Wei Chen, Zhiyuan Li

cs.AI

摘要

语言模型在各种应用中表现出色，然而最复杂的模型通常是专有的。例如，OpenAI 的 GPT-4 和 Anthropic 的各种模型价格昂贵且消耗大量能源。相比之下，开源社区已经产生了竞争性模型，比如 Llama3。此外，针对特定领域的较小语言模型，比如针对法律、医疗或金融任务定制的模型，已经超越了它们的专有对手。本文介绍了一种新方法，利用功能标记来整合多个针对特定任务进行优化的开源模型。我们新开发的 Octopus v4 模型利用功能标记智能地引导用户查询到最合适的垂直模型，并重新格式化查询以获得最佳性能。Octopus v4 是 Octopus v1、v2 和 v3 模型的进化，在选择和参数理解以及重新格式化方面表现出色。此外，我们探讨了将图形作为一种多功能数据结构的使用，通过利用 Octopus 模型和功能标记的能力有效协调多个开源模型。使用我们的开源 GitHub（https://www.nexa4ai.com/）尝试 Octopus v4 模型（https://huggingface.co/NexaAIDev/Octopus-v4），并贡献到更大的语言模型图中。通过激活少于 10B 参数的模型，我们在相同级别模型中实现了 74.8 的 SOTA MMLU 分数。

English

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 functional tokens to integrate multiple open-source models, each optimized for particular tasks. Our newly developed Octopus v4 model leverages 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 functional tokens. Use our open-sourced GitHub (https://www.nexa4ai.com/) to try Octopus v4 models (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.