小模型也能在设备端完成专业任务，兼顾性能与隐私。
Fine-Tuning Small Language Models for Domain-Specific AI: An Edge AI Perspective
- 用轻量架构+量化+责任AI设计小模型，适配边缘设备。
- 在医疗、金融、法律等场景表现超越预期，通用任务也达标。
- 适合手机、IoT等资源受限的智能终端使用。
将大语言模型部署在边缘设备面临计算需求高、能耗大和数据隐私风险等问题。本文提出针对这些挑战的Shakti系列小语言模型（Shakti-100M、Shakti-250M、Shakti-500M），通过高效架构、量化技术与负责任AI原则，实现智能手机、智能家电、物联网系统等设备上的本地化智能。提供对模型设计哲学、训练流程及在通用任务（如MMLU、Hellaswag）和专业领域（医疗、金融、法律）上基准性能的全面分析。研究显示，经过精心设计和微调的小模型，在真实边缘AI场景中不仅能满足需求，常可超越预期。
原文摘要 · Abstract (English)
Deploying large scale language models on edge devices faces inherent challenges such as high computational demands, energy consumption, and potential data privacy risks. This paper introduces the Shakti Small Language Models (SLMs) Shakti-100M, Shakti-250M, and Shakti-500M which target these constraints headon. By combining efficient architectures, quantization techniques, and responsible AI principles, the Shakti series enables on-device intelligence for smartphones, smart appliances, IoT systems, and beyond. We provide comprehensive insights into their design philosophy, training pipelines, and benchmark performance on both general tasks (e.g., MMLU, Hellaswag) and specialized domains (healthcare, finance, and legal). Our findings illustrate that compact models, when carefully engineered and fine-tuned, can meet and often exceed expectations in real-world edge-AI scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。