Strategije prilagajanja izhodov velikih jezikovnih modelov

magistrsko delo

Bard Grujič (Author), Sašo Karakatič (Mentor)

Abstract

Namen magistrskega dela je sistematično predstaviti, raziskati in analizirati delovanje velikih jezikovnih modelov, s posebnim poudarkom na modelu transformatorja, ter raziskati, kako prilagoditi izhode teh modelov za specifične potrebe organizacij. V praksi bomo preučili, kako ta prilagoditev deluje, tako da bomo razvili in demonstrirali aplikacijo za iskanje ključnih besed po dokumentih v PDF formatu z uporabo velikega jezikovnega modela GPT-4 podjetja OpenAI.

Keywords

veliki jezikovni modeli;modeli obdelave naravnega jezika;umetna inteligenca;inženiring spodbud;magistrske naloge;

Data

Language:	Slovenian
Year of publishing:	2024
Typology:	2.09 - Master's Thesis
Organization:	UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher:	[B. Grujič]
UDC:	004.8:81'322.2(043.2)
COBISS:	219233283
Views:	0
Downloads:	15
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Strategies for adjusting the outputs of large language models
Secondary abstract:	The purpose of this master's thesis is to systematically present, investigate, and analyze the operation of large language models, with a particular focus on the transformer model, and to explore how to adapt the outputs of these models to meet the specific needs of organizations. In practice, we will examine how this adaptation works by developing and demonstrating an application for keyword search in PDF documents using the GPT-4 large language model developed by OpenAI.
Secondary keywords:	large language models;natural language processing models;artificial intelligence;prompt engineering;master's theses;
Type (COBISS):	Master's thesis/paper
Thesis comment:	Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Informatika in tehnologije komuniciranja
Pages:	1 spletni vir (1 datoteka PDF (VIII, 84 f.))
ID:	24708244