會議論文
| 學年 | 114 |
|---|---|
| 學期 | 1 |
| 發表日期 | 2025-11-20 |
| 作品名稱 | Cubicpower Agentic Mixture of Experts(AMoE) Framework for Fine-Tuning NLP Tasks Without GPUs |
| 作品名稱（其他語言） | |
| 著者 | Chao-Yih Hsia 夏肇毅 |
| 作品所屬單位 | |
| 出版者 | |
| 會議名稱 | ROCLING 2025 |
| 會議地點 | 台北市，臺灣 |
| 摘要 | The rise of Green AI emphasizes minimizing the environmental footprint of AI systems. This paper explores a no-GPU agentic architecture for fine-tuning NLP tasks. It presents our initial experiments applying these no-GPU algorithms in pretraining and fine-tuning tasks on our CubicPower agentic mixture of experts (AMoE) framework, with the aim of contributing to more sustainable AI development. In contrast to the training procedures of neural networks, which consume significant power, the AMoE framework’s primary contribution toward power savings is that it requires no training process. We explore non-neural-network methods for solving NLP tasks and employ similarity measures to match predefined patterns for use in a RAG database. https://drive.google.com/file/d/1DIGJzMJbrQxWuuSeouYsVwa0mnhYvrD2/view?usp=sharing |
| 關鍵字 | Green AI;MoE;RAG;CubicPower;AMoE;CubicPower |
| 語言 | en |
| 收錄於 | |
| 會議性質 | 國際 |
| 校內研討會地點 | 無 |
| 研討會時間 | 20251120~20251122 |
| 通訊作者 | |
| 國別 | TWN |
| 公開徵稿 | |
| 出版型式 | |
| 出處 | |
| 相關連結 |
機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/128261 ) |