SHAKTI：一款针对边缘人工智能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

October 15, 2024

作者: Syed Abdul Gaffar Shakhadri, Kruthika KR, Rakshit Aralimatti

cs.AI

摘要

我们介绍Shakti，这是一个专门针对资源受限环境（如边缘设备，包括智能手机、可穿戴设备和物联网系统）进行优化的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，使其非常适用于计算资源和内存有限的实时人工智能应用。Shakti支持方言语言和领域特定任务，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在维持低延迟和设备效率的同时，与更大的模型竞争力强，使其成为边缘人工智能领域的领先解决方案。

English

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.