SHAKTI：一個針對邊緣人工智慧和低資源環境優化的擁有 25 億參數的小型語言模型

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

我們介紹Shakti，這是一個擁有25億參數的語言模型，專門為資源受限環境（如邊緣裝置，包括智慧手機、可穿戴裝置和物聯網系統）進行了優化。Shakti結合了高性能自然語言處理（NLP）與優化的效率和精確性，使其非常適合於計算資源和記憶體有限的實時人工智慧應用。支援方言語言和特定領域任務，Shakti在醫療保健、金融和客戶服務等行業表現卓越。基準評估顯示，Shakti在維持低延遲和設備效率的同時，與更大的模型競爭力強，使其成為邊緣人工智慧的領先解決方案。

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.