It looks like you're using Internet Explorer 11 or older. This website works best with modern browsers such as the latest versions of Chrome, Firefox, Safari, and Edge. If you continue with this browser, you may see unexpected results.
  • AWARDS
  • WORKS
      • ALL
      • SCHOOLS & OFFICES
          • SCHOOL OF ARTS AND SOCIAL SCIENCES
          • LEE SHAU KEE SCHOOL OF BUSINESS AND ADMINISTRATION
          • SCHOOL OF EDUCATION AND LANGUAGES
          • SCHOOL OF NURSING AND HEALTH STUDIES
          • SCHOOL OF SCIENCE AND TECHNOLOGY
          • LI KA SHING SCHOOL OF PROFESSIONAL AND CONTINUING EDUCATION (LiPACE)
          • LIBRARY
          • STUDENT AFFAIRS OFFICE
      • COLLECTIONS
  • ABOUT
Search
Advanced Search
Log In
繁
简
close×
  • Home
  • S&T Best Computing Projects

Vertical language model based on SingSharp's knowledge base

Twitter logo Weibo logo Whatsapp logo Facebook logo Mail logo
Part of: Vertical language model based on SingSharp's knowledge base (3 objects)
Previous3 of 3
Vertical language model based on SingSharp's knowledge base - pdf
Vertical language model based on SingSharp's knowledge base - video1
Vertical language model based on SingSharp's knowledge base - video2
Collection
  • S&T Best Computing Projects
Record Details
Record ID
stcompfyp:183
Title
Vertical language model based on SingSharp's knowledge base
Type of Work
Final Year Project/Work
Collection
S&T Best Computing Projects
Contributor
Leung, Chun Hung Jonas (group member)
Kuai, Le (group member)
Yi, Yicheng (group member)
Li, Zongxi Roy 李宗禧 (supervisor)
School / Unit
School of Science and Technology (S&T) 
Program
Bachelor of Computing with Honours in Internet Technology
Date
2024
Abstract
The aim of this project is to implement a RAG framework to enhance the effectiveness of the LLaMA-2 model within the singing domain. By employing Semantic Textual Similarity (STS) techniques, the model will retrieve the most relevant context from the vocal arts specialized knowledge base on singing.
Type of Resource
Mixed
Language
English
Physical Description
This work includes 1 PDF file and 2 video clips.
Access Eligibility
Public Access
Permanent Link
https://repository.lib.hkmu.edu.hk/sw/islandora/object/stcompfyp:183
Object Details
Record ID
stcompfyp:184
Title
Vertical language model based on SingSharp's knowledge base - video2
Collection
S&T Best Computing Projects
Type of Resource
Video
Physical Description
3 minutes 2 seconds.
Access Eligibility
Public Access
Permanent Link
https://repository.lib.hkmu.edu.hk/sw/islandora/object/stcompfyp:184
Responsible Use of Electronic Resources
Internet Policy and Disclaimer
© Hong Kong Metropolitan University. All Rights Reserved.