SHAKTI:一个为边缘AI和低资源环境优化的25亿参数小型语言模型
SHAKTI: A 2.5 Billion Parameter Small Language Model Optimized for Edge AI and Low-Resource Environments
AI总结:
本文提出25亿参数的边缘AI语言模型Shakti,兼顾高性能与低资源效率,支持本地语言,在医疗、金融等领域表现优异,性能媲美大模型且延迟低。
摘要:
我们介绍了Shakti,一个专门为资源受限环境(如智能手机、可穿戴设备和物联网系统等边缘设备)优化的25亿参数语言模型。Shakti将高性能自然语言处理与优化的效率和精度相结合,使其非常适合计算资源和内存有限的实时AI应用。凭借对本地语言和领域特定任务的支持,Shakti在医疗保健、金融和客户服务等行业表现出色。基准评估表明,Shakti在保持低延迟和设备端效率的同时,其性能可与更大的模型相媲美,使其成为边缘AI的领先解决方案。
英文摘要:
We introduce Shakti, a 2.5 billion parameter language model specifically optimized for resource-constrained environments such as edge devices, including smartphones, wearables, and IoT systems. Shakti combines high-performance NLP with optimized efficiency and precision, making it ideal for real-time AI applications where computational resources and memory are limited. With support for vernacular languages and domain-specific tasks, Shakti excels in industries such as healthcare, finance, and customer service. Benchmark evaluations demonstrate that Shakti performs competitively against larger models while maintaining low latency and on-device efficiency, positioning it as a leading solution for edge AI.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。