The Future of Octopus v2: What Does it Entail?

Table of Links

Abstract and 1. Introduction

2 Related works

3 Methodology and 3.1 Causal language model as a classification model

3.2 Functional token

3.3 Dataset collection

3.4 Model development and training

4 Experiments and 4.1 Android function calls

4.2 Extension to Vehicle, Yelp, and DoorDash function sets

4.3 Full and partial training datasets and 4.4 Full training and LoRA training

4.5 Parallel and nested function call and 4.6 Weighted loss function for special tokens

5 Discussion and future works and References

Appendix

A.1 Android function examples

A.2 Vehicle function examples

5 Discussion and future works

Our current training initiative proves that any specific function can be encapsulated into a newly coined term, functional token, a novel token type seamlessly integrated into both the tokenizer and the model. This model, through a cost-effective training process amounting to merely two cents, facilitates the deployment of AI agents characterized by their remarkably low latency and high accuracy.

The potential impacts of our research are extensive. For application developers, including those at DoorDash and Yelp, our model paves the way for training on application-specific scenarios. Developers can pinpoint the APIs most utilized by their audience, transform these into functional tokens for the Octopus model, and proceed with deployment. This strategy has the capacity to fully

automate app workflows, emulating functionalities akin to Apple’s Siri, albeit with significantly enhanced response speeds and accuracy.

Furthermore, the model’s application within operating systems of PCs, smartphones, and wearable technology presents another exciting avenue. Software developers could train minor LoRAs specific to the operating system. By accumulating multiple LoRAs, the model facilitates efficient function calling across diverse system components. For instance, incorporating this model into the Android ecosystem would enable Yelp and DoorDash developers to train distinct LoRAs, thus rendering the model operational on mobile platforms as well.

Looking ahead, we aim to develop a model dedicated to on-device reasoning. Our ambitions are dual-pronged: firstly, to achieve notable speed enhancements for cloud deployments, vastly outpacing GPT-4 in speed metrics. Secondly, to support local deployment, offering a valuable solution for users mindful of privacy or operational costs. This dual deployment strategy not only extends the model’s utility across cloud and local environments, but also caters to user preferences for either speed and efficiency or privacy and cost savings.

References

[1] Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. Gpt-4 technical report. arXiv preprint arXiv:2303.08774, 2023.

[2] Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901, 2020.

[3] Erik Brynjolfsson, Danielle Li, and Lindsey R Raymond. Generative ai at work. Technical report, National Bureau of Economic Research, 2023. [4] Rich Caruana. Multitask learning. Machine learning, 28:41–75, 1997.

[5] Imran Chaudhri. Humane ai, 2024. URL https://humane.com/. Accessed on March 31, 2024.

[6] Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer. Qlora: Efficient finetuning of quantized llms. Advances in Neural Information Processing Systems, 36, 2024.

[7] Xin Luna Dong, Seungwhan Moon, Yifan Ethan Xu, Kshitiz Malik, and Zhou Yu. Towards next-generation intelligent assistants leveraging llm techniques. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 5792–5793, 2023.

[8] Yu Du, Fangyun Wei, and Hongyang Zhang. Anytool: Self-reflective, hierarchical agents for large-scale api calls. arXiv preprint arXiv:2402.04253, 2024.

[9] Div Garg. Multion ai, 2024. URL https://www.multion.ai/. Accessed on March 31, 2024.

[10] Gemma Team, Google DeepMind. Gemma: Open models based on gemini research and technology, 2023. URL https://goo.gle/GemmaReport.

[11] Allyson I Hauptman, Beau G Schelble, Nathan J McNeese, and Kapil Chalil Madathil. Adapt and overcome: Perceptions of adaptive autonomous agents for human-ai teaming. Computers in Human Behavior, 138: 107451, 2023.

[12] Sirui Hong, Xiawu Zheng, Jonathan Chen, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, et al. Metagpt: Meta programming for multi-agent collaborative framework. arXiv preprint arXiv:2308.00352, 2023.

[13] Yining Hong, Haoyu Zhen, Peihao Chen, Shuhong Zheng, Yilun Du, Zhenfang Chen, and Chuang Gan. 3d-llm: Injecting the 3d world into large language models. Advances in Neural Information Processing Systems, 36:20482–20494, 2023.

[14] Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685, 2021.

[15] Zhengbao Jiang, Frank F Xu, Luyu Gao, Zhiqing Sun, Qian Liu, Jane Dwivedi-Yu, Yiming Yang, Jamie Callan, and Graham Neubig. Active retrieval augmented generation. arXiv preprint arXiv:2305.06983, 2023.

[16] Zhanming Jie, Trung Quoc Luong, Xinbo Zhang, Xiaoran Jin, and Hang Li. Design of chain-of-thought in math problem solving, 2023.

[17] Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. Retrieval-augmented generation for knowledgeintensive nlp tasks. Advances in Neural Information Processing Systems, 33:9459–9474, 2020.

[18] Bo Li, Yuanhan Zhang, Liangyu Chen, Jinghao Wang, Fanyi Pu, Jingkang Yang, Chunyuan Li, and Ziwei Liu. Mimic-it: Multi-modal in-context instruction tuning. arXiv preprint arXiv:2306.05425, 2023.

[19] Huayang Li, Yixuan Su, Deng Cai, Yan Wang, and Lemao Liu. A survey on retrieval-augmented text generation. arXiv preprint arXiv:2202.01110, 2022.

[20] Yaobo Liang, Chenfei Wu, Ting Song, Wenshan Wu, Yan Xia, Yu Liu, Yang Ou, Shuai Lu, Lei Ji, Shaoguang Mao, et al. Taskmatrix. ai: Completing tasks by connecting foundation models with millions of apis. arXiv preprint arXiv:2303.16434, 2023.

[21] Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Xingyu Dang, and Song Han. Awq: Activation-aware weight quantization for llm compression and acceleration. arXiv preprint arXiv:2306.00978, 2023.

[22] Yi Liu, Gelei Deng, Yuekang Li, Kailong Wang, Tianwei Zhang, Yepang Liu, Haoyu Wang, Yan Zheng, and Yang Liu. Prompt injection attack against llm-integrated applications. arXiv preprint arXiv:2306.05499, 2023.

[23] Zechun Liu, Changsheng Zhao, Forrest Iandola, Chen Lai, Yuandong Tian, Igor Fedorov, Yunyang Xiong, Ernie Chang, Yangyang Shi, Raghuraman Krishnamoorthi, et al. Mobilellm: Optimizing sub-billion parameter language models for on-device use cases. arXiv preprint arXiv:2402.14905, 2024.

[24] llama.cpp team. llama-cpp. Software available at https://github.com/ggerganov/llama.cpp, 2023. Accessed on March 31, 2024.

[25] David Luan. Adept ai, 2024. URL https://www.adept.ai/. Accessed on March 31, 2024.

[26] Jesse Lyu. Rabbit r1, 2024. URL https://www.rabbit.tech/. Accessed on March 31, 2024.

[27] Yuning Mao, Pengcheng He, Xiaodong Liu, Yelong Shen, Jianfeng Gao, Jiawei Han, and Weizhu Chen. Generation-augmented retrieval for open-domain question answering. arXiv preprint arXiv:2009.08553, 2020.

[28] Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781, 2013.

[29] Bhargavi Paranjape, Scott Lundberg, Sameer Singh, Hannaneh Hajishirzi, Luke Zettlemoyer, and Marco Tulio Ribeiro. Art: Automatic multi-step reasoning and tool-use for large language models. arXiv preprint arXiv:2303.09014, 2023.

[30] Shishir G Patil, Tianjun Zhang, Xin Wang, and Joseph E Gonzalez. Gorilla: Large language model connected with massive apis. arXiv preprint arXiv:2305.15334, 2023.

[31] Nikhil Pinnaparaju, Reshinth Adithyan, Duy Phung, Jonathan Tow, James Baicoianu, and Nathan Cooper. Stable code 3b, 2023. URL https://huggingface.co/stabilityai/stable-code-3b.

[32] Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan Yan, Yaxi Lu, Yankai Lin, Xin Cong, Xiangru Tang, Bill Qian, et al. Toolllm: Facilitating large language models to master 16000+ real-world apis. arXiv preprint arXiv:2307.16789, 2023.

[33] Alec Radford, Karthik Narasimhan, Tim Salimans, Ilya Sutskever, et al. Improving language understanding by generative pre-training. OpenAI blog, 2018.

[34] Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9, 2019.

[35] Ori Ram, Yoav Levine, Itay Dalmedigos, Dor Muhlgay, Amnon Shashua, Kevin Leyton-Brown, and Yoav Shoham. In-context retrieval-augmented language models. Transactions of the Association for Computational Linguistics, 11:1316–1331, 2023.

[36] Jingqing Ruan, Yihong Chen, Bin Zhang, Zhiwei Xu, Tianpeng Bao, Guoqing Du, Shiwei Shi, Hangyu Mao, Xingyu Zeng, and Rui Zhao. Tptu: Task planning and tool usage of large language model-based ai agents. arXiv preprint arXiv:2308.03427, 2023.

[37] Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Eric Hambro, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. Toolformer: Language models can teach themselves to use tools. Advances in Neural Information Processing Systems, 36, 2024.

[38] Weizhou Shen, Chenliang Li, Hongzhan Chen, Ming Yan, Xiaojun Quan, Hehong Chen, Ji Zhang, and Fei Huang. Small llms are weak tool learners: A multi-llm agent. arXiv preprint arXiv:2401.07324, 2024.

[39] Yongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li, Weiming Lu, and Yueting Zhuang. Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face. Advances in Neural Information Processing Systems, 36, 2024.

[40] Noah Shinn, Beck Labash, and Ashwin Gopinath. Reflexion: an autonomous agent with dynamic memory and self-reflection. arXiv preprint arXiv:2303.11366, 2023.

[41] Benjamin Spector and Chris Re. Accelerating llm inference with staged speculative decoding. arXiv preprint arXiv:2308.04623, 2023.

[42] Venkat Krishna Srinivasan, Zhen Dong, Banghua Zhu, Brian Yu, Damon Mosk-Aoyama, Kurt Keutzer, Jiantao Jiao, and Jian Zhang. Nexusraven: a commercially-permissive language model for function calling. In NeurIPS 2023 Foundation Models for Decision Making Workshop, 2023.

[43] Yashar Talebirad and Amirhossein Nadiri. Multi-agent collaboration: Harnessing the power of intelligent llm agents. arXiv preprint arXiv:2306.03314, 2023.

[44] Qiaoyu Tang, Ziliang Deng, Hongyu Lin, Xianpei Han, Qiao Liang, and Le Sun. Toolalpaca: Generalized tool learning for language models with 3000 simulated cases. arXiv preprint arXiv:2306.05301, 2023.

[45] Gemini Team, Rohan Anil, Sebastian Borgeaud, Yonghui Wu, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M Dai, Anja Hauth, et al. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805, 2023.

[46] MLC team. Mlc-llm. Software available at https://github.com/mlc-ai/mlc-llm, 2023. Accessed on March 31, 2024.

[47] Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, et al. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288, 2023.

[48] Trelis. Llama-2-7b-chat-hf-function-calling-v3: A model fine-tuned for function calling. Hugging Face Model Repository, 2023. URL https://huggingface.co/Trelis/ Llama-2-7b-chat-hf-function-calling-v3. Accessed on March 31, 2024.

[49] Junyang Wang, Haiyang Xu, Jiabo Ye, Ming Yan, Weizhou Shen, Ji Zhang, Fei Huang, and Jitao Sang. Mobile-agent: Autonomous multi-modal mobile device agent with visual perception. arXiv preprint arXiv:2401.16158, 2024.

[50] Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, Yankai Lin, et al. A survey on large language model based autonomous agents. arXiv preprint arXiv:2308.11432, 2023.

[51] Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35:24824–24837, 2022.

[52] Hao Wen, Yuanchun Li, Guohong Liu, Shanhui Zhao, Tao Yu, Toby Jia-Jun Li, Shiqi Jiang, Yunhao Liu, Yaqin Zhang, and Yunxin Liu. Empowering llm to use smartphone for intelligent task automation. arXiv preprint arXiv:2308.15272, 2023.

[53] Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Shaokun Zhang, Erkang Zhu, Beibin Li, Li Jiang, Xiaoyun Zhang, and Chi Wang. Autogen: Enabling next-gen llm applications via multi-agent conversation framework. arXiv preprint arXiv:2308.08155, 2023.

[54] Zhiheng Xi, Wenxiang Chen, Xin Guo, Wei He, Yiwen Ding, Boyang Hong, Ming Zhang, Junzhe Wang, Senjie Jin, Enyu Zhou, et al. The rise and potential of large language model based agents: A survey. arXiv preprint arXiv:2309.07864, 2023.

[55] Daliang Xu, Wangsong Yin, Xin Jin, Ying Zhang, Shiyun Wei, Mengwei Xu, and Xuanzhe Liu. Llmcad: Fast and scalable on-device large language model inference. arXiv preprint arXiv:2309.04255, 2023.

[56] Zhao Yang, Jiaxuan Liu, Yucheng Han, Xin Chen, Zebiao Huang, Bin Fu, and Gang Yu. Appagent: Multimodal agents as smartphone users. arXiv preprint arXiv:2312.13771, 2023.

[57] Yifan Yao, Jinhao Duan, Kaidi Xu, Yuanfang Cai, Zhibo Sun, and Yue Zhang. A survey on large language model (llm) security and privacy: The good, the bad, and the ugly. High-Confidence Computing, page 100211, 2024.

[58] Zhuosheng Zhang, Aston Zhang, Mu Li, and Alex Smola. Automatic chain of thought prompting in large language models. arXiv preprint arXiv:2210.03493, 2022.