The field of Artificial Intelligence has witnessed remarkable progress in recent years, especially with the emergence of powerful large language models (LLMs) based on the transformer architecture. Cloud-based LLMs, such as OpenAI's ChatGPT, offer impressive capabilities but come with concerns regarding latency and privacy due to network dependencies. This article presents an innovative approach to LLM inference, envisioning a future where LLMs with billions of parameters can be executed directly on mobile devices without network connectivity. The article showcases a fine-tuned GPT LLM with 3 billion parameters that can operate smoothly on devices with as low as 4GB of memory. Through the integration of native code and model quantization techniques, the application not only serves as a general-purpose assistant but also facilitates seamless mobile interactions with text-to-actions features. The article provides insights into the training pipeline, implementation details, test results, and future directions of on-device LLM inference. This breakthrough technology opens up possibilities for empowering users with sophisticated AI capabilities while preserving their privacy and eliminating latency concerns.
What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers
NAVER CLOVA；NAVER AI Lab；NAVER Search；Search Solutions Inc（Search Solutions公司）
GPT-3显示出在数千亿规模数据上训练的大规模语言模型（LM）的显着上下文学习能力。在这里，我们解决了GPT-3论文中较少报道的一些剩余问题，例如非英语LM，不同大小模型的性能，以及最近引入的即时优化对上下文学习的影响。为了实现这一目标，我们引入了HyperCLOVA，这是82 B GPT-3的韩国变体，在以韩国为中心的560 B令牌语料库上进行了训练。通过我们的韩语特定标记化增强，HyperCLOVA与我们的训练配置在韩语的各种下游任务上显示了最先进的上下文zero-shot和少样本学习性能。此外，我们展示了基于机器学习的性能优势，并演示了如何将其集成到提示工程管道中。然后，我们讨论了通过引入HyperCLOVA工作室（一个交互式提示工程界面）为ML的非专家提供AI原型设计功能来实现无代码AI范式的可能性。最后，我们展示了我们的方法与三个成功的内部应用程序的潜力。
Revolutionizing Finance with LLMs: An Overview of Applications and Insights
School of Computing, The University of Georgia（佐治亚大学计算机学院）；Computer Science and Engineering, The University of Texas at Arlington（德克萨斯大学阿灵顿分校计算机科学与工程系）；Department of Geography, University of Georgia（佐治亚大学地理系）
It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners
LMU Munich（慕尼黑大学）；Sulzer GmbH（苏尔寿有限公司）
当缩放到数千亿个参数时，预训练的语言模型，例如GPT-3（Brown et al.，2020）实现了卓越的Few-Shot性能。然而，训练和应用这些大型模型需要大量的计算，导致大量的碳足迹，使研究人员和从业人员难以使用它们。我们表明，可以获得类似于GPT-3的性能与语言模型，是“绿色”，因为他们的参数计数是几个数量级小。这是通过将文本输入转换为包含任务描述的完形填空题，结合基于梯度的优化来实现的;利用未标记的数据可以进一步改进。我们确定成功的自然语言理解所需的关键因素与小语言模型。
SurgicalGPT: End-to-End Language-Vision GPT for Visual Question Answering in Surgery
National University of Singapore（新加坡国立大学）；University College London（伦敦大学学院）；National Institute of Technology, Tiruchirappalli（蒂鲁吉拉伯利国立理工学院）；Chinese University of Hong Kong（香港中文大学）；Shun Hing Institute of Advanced Engineering, Chinese University of Hong Kong（香港中文大学信兴高等工程研究所）
Superhuman performance in urology board questions by an explainable large language model enabled for context integration of the European Association of Urology guidelines: the UroBot study
German Cancer Research Center (DKFZ)（德国癌症研究中心）；University Medical Center Mannheim, Ruprecht-Karls University of Heidelberg（海德堡大学曼海姆医学院）；University of Heidelberg（海德堡大学）
An LLM-Powered Agent for Physiological Data Analysis: A Case Study on PPG-based Heart Rate Estimation
Department of Computing, University of Turku（图波卡大学计算机系）；Department of Computer Science, University of California, Irvine（加州大学伊文斯顿分校计算机科学系）；School of Nursing, University of California, Irvine（加州大学伊文斯顿分校护理学院）
Can GPT-4 Help Detect Quit Vaping Intentions? An Exploration of Automatic Data Annotation Approach
HI3 Tech Lab, University of South Carolina（南卡罗来纳大学HI3技术实验室）；School of Medicine, Washington University（华盛顿大学医学院）；University of Texas Health Science Center（德克萨斯大学健康科学中心）
MobiLlama: Towards Accurate and Lightweight Fully Transparent GPT
Mohamed bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）；Australian National University（澳大利亚国立大学）；Aalto University（阿尔托大学）；The University of Melbourne（墨尔本大学）；Linköping University（林雪平大学）
SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；University of Oxford（牛津大学）；Peking University（北京大学）
Med-V1: Small Language Models for Zero-shot and Scalable Biomedical Evidence Attribution
Division of Intramural Research, National Library of Medicine, National Institutes of Health（国家医学图书馆内部研究部，国立卫生研究院）；Department of Computer Science, University of Virginia（弗吉尼亚大学计算机科学系）；Center for Cancer Research, National Cancer Institute, National Institutes of Health（国家癌症研究所癌症研究中心，国立卫生研究院）；Department of Population Health Sciences, Weill Cornell Medicine Institute of AI for Digital Health, Weill Cornell Medicine（韦尔·科恩医学中心流行病学与健康科学系，韦尔·科恩医学中心人工智能与数字健康研究所）
