Fine-Tuning Small Language Models for Domain-Specific AI: An Edge AI Perspective
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918162135515136 |
|---|---|
| author | Aralimatti, Rakshit Shakhadri, Syed Abdul Gaffar KR, Kruthika Angadi, Kartik Basavaraj |
| author_facet | Aralimatti, Rakshit Shakhadri, Syed Abdul Gaffar KR, Kruthika Angadi, Kartik Basavaraj |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_01933 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fine-Tuning Small Language Models for Domain-Specific AI: An Edge AI Perspective Aralimatti, Rakshit Shakhadri, Syed Abdul Gaffar KR, Kruthika Angadi, Kartik Basavaraj Machine Learning Hardware Architecture Computation and Language Computer Vision and Pattern Recognition 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. |
| title | Fine-Tuning Small Language Models for Domain-Specific AI: An Edge AI Perspective |
| topic | Machine Learning Hardware Architecture Computation and Language Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.01933 |