國立虎尾科技大學 |

Optimizing Large Language Models for Edge Devices : = A Comparative Study on Reputation Analysis.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Optimizing Large Language Models for Edge Devices :/
其他題名:	A Comparative Study on Reputation Analysis.
作者:	Rahman, Mohammad Wali Ur.
面頁冊數:	1 online resource (91 pages)
附註:	Source: Masters Abstracts International, Volume: 85-05.
Contained By:	Masters Abstracts International85-05.
標題:	Web studies. -
電子資源:	click for full text (PQDT)
ISBN:	9798380843867

Optimizing Large Language Models for Edge Devices : = A Comparative Study on Reputation Analysis.
Rahman, Mohammad Wali Ur.

Optimizing Large Language Models for Edge Devices :A Comparative Study on Reputation Analysis. - 1 online resource (91 pages)

Source: Masters Abstracts International, Volume: 85-05.

Thesis (M.S.)--The University of Arizona, 2023.

Includes bibliographical references

The widespread adoption of social media platforms has led to an exponential surge in user-generated data, shaping the reputations of companies and public figures on a global scale. Consequently, reputation management through automated analysis has become indispensable. Recent advances in large-scale language models, such as BERT (Bidirectional Encoder Representations from Transformers), have shown remarkable success in Natural Language Processing (NLP) tasks. However, deploying such models on resource-constrained edge devices remains challenging due to their size and computational demands.In this thesis, we focus on optimizing large language models for edge devices with limited resources by conducting a comparative study. Our investigation centers around reputation analysis, a critical NLP task, to assess the feasibility and efficiency of deploying transformer-based models on edge devices. We fine-tune MobileBERT, a compact version of BERT, on the reputation polarity task using the RepLab 2013 dataset. To enable their deployment on edge devices, we utilize TensorFlow-Lite models and apply quantization techniques for model optimization.The experimental results demonstrate the efficacy of our approach. The quantized MobileBERT models showcase comparable performance to the original BERT model, with only a marginal 4.1\\% drop in accuracy. More importantly, the optimized models exhibit a significant reduction in model size, boasting a 160x smaller footprint, and achieve faster inference times. These results validate the practical applicability of transformer-based reputation analysis on edge devices, making them an attractive solution for real-world deployments.In conclusion, this thesis showcases the potential of optimizing large language models for resource-constrained edge devices. Through a rigorous comparative study, we demonstrate that transformer-based models can be effectively deployed for reputation analysis on edge devices without compromising performance. This research paves the way for leveraging advanced NLP techniques in real-world applications, where efficient edge device implementation is essential, opening new possibilities for a wide range of edge computing scenarios beyond reputation analysis.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798380843867Subjects--Topical Terms:

1148502
Web studies.
Subjects--Index Terms:

Social media platformsIndex Terms--Genre/Form:

554714
Electronic books.

Optimizing Large Language Models for Edge Devices : = A Comparative Study on Reputation Analysis.
LDR:03570ntm a22003737 4500 001 1143670
005 20240517104626.5
006 m o d
007 cr mn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798380843867
035 $a (MiAaPQ)AAI30694608
035 $a AAI30694608
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Rahman, Mohammad Wali Ur. $3 1468427
245 1 0 $a Optimizing Large Language Models for Edge Devices : $b A Comparative Study on Reputation Analysis.
264 0 $c 2023
300 $a 1 online resource (91 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 85-05.
500 $a Advisor: Hariri, Salim.
502 $a Thesis (M.S.)--The University of Arizona, 2023.
504 $a Includes bibliographical references
520 $a The widespread adoption of social media platforms has led to an exponential surge in user-generated data, shaping the reputations of companies and public figures on a global scale. Consequently, reputation management through automated analysis has become indispensable. Recent advances in large-scale language models, such as BERT (Bidirectional Encoder Representations from Transformers), have shown remarkable success in Natural Language Processing (NLP) tasks. However, deploying such models on resource-constrained edge devices remains challenging due to their size and computational demands.In this thesis, we focus on optimizing large language models for edge devices with limited resources by conducting a comparative study. Our investigation centers around reputation analysis, a critical NLP task, to assess the feasibility and efficiency of deploying transformer-based models on edge devices. We fine-tune MobileBERT, a compact version of BERT, on the reputation polarity task using the RepLab 2013 dataset. To enable their deployment on edge devices, we utilize TensorFlow-Lite models and apply quantization techniques for model optimization.The experimental results demonstrate the efficacy of our approach. The quantized MobileBERT models showcase comparable performance to the original BERT model, with only a marginal 4.1\\% drop in accuracy. More importantly, the optimized models exhibit a significant reduction in model size, boasting a 160x smaller footprint, and achieve faster inference times. These results validate the practical applicability of transformer-based reputation analysis on edge devices, making them an attractive solution for real-world deployments.In conclusion, this thesis showcases the potential of optimizing large language models for resource-constrained edge devices. Through a rigorous comparative study, we demonstrate that transformer-based models can be effectively deployed for reputation analysis on edge devices without compromising performance. This research paves the way for leveraging advanced NLP techniques in real-world applications, where efficient edge device implementation is essential, opening new possibilities for a wide range of edge computing scenarios beyond reputation analysis.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Web studies. $3 1148502
650 4 $a Electrical engineering. $3 596380
650 4 $a Computer science. $3 573171
653 $a Social media platforms
653 $a Natural Language Processing
653 $a Reputation analysis
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0544
690 $a 0646
710 2 $a The University of Arizona. $b Electrical & Computer Engineering. $3 1189571
710 2 $a ProQuest Information and Learning Co. $3 1178819
773 0 $t Masters Abstracts International $g 85-05.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30694608 $z click for full text (PQDT)