Location

https://www.kennesaw.edu/ccse/events/computing-showcase/fa24-cday-program.php

Streaming Media

Document Type

Event

Start Date

19-11-2024 4:00 PM

Description

This project focuses on developing a domain-specific chatbot tailored for the tech industry. The chatbot utilizes articles sourced from blogs written by developers and engineers at leading companies such as Google and NVIDIA. Titles and content from these articles are extracted to form a question-answer dataset, with the titles acting as questions and the article content serving as answers. To refine the questions, we implemented a custom method to format the dataset to follow Alpaca format. The resulting question-answer pairs are then used to fine-tune a language model, adapting it to the specialized domain of the tech industry. Following this, the model undergoes rigorous evaluation to ensure its accuracy and relevance, and iterative improvements are made based on performance metrics. The final product is deployed as a chatbot capable of handling complex queries in the tech space, offering valuable support to developers and engineers.

Share

COinS
 
Nov 19th, 4:00 PM

GPR-2238 Tech Guru: A Domain Specific LLM for Tech. Industry​

https://www.kennesaw.edu/ccse/events/computing-showcase/fa24-cday-program.php

This project focuses on developing a domain-specific chatbot tailored for the tech industry. The chatbot utilizes articles sourced from blogs written by developers and engineers at leading companies such as Google and NVIDIA. Titles and content from these articles are extracted to form a question-answer dataset, with the titles acting as questions and the article content serving as answers. To refine the questions, we implemented a custom method to format the dataset to follow Alpaca format. The resulting question-answer pairs are then used to fine-tune a language model, adapting it to the specialized domain of the tech industry. Following this, the model undergoes rigorous evaluation to ensure its accuracy and relevance, and iterative improvements are made based on performance metrics. The final product is deployed as a chatbot capable of handling complex queries in the tech space, offering valuable support to developers and engineers.