Technical Workshop Series
Getting to Know Llama (your own ChatGPT) - Part 2 (1st Offering)
Presenter: Ali Forooghi
Date: Thursday, 30 May 2024
Time: 1:00 pm
Location: 4th Floor (Lecture Space) at 300 Ouellette Avenue (School of Computer Science Advanced Computing Hub)
Reminders: This is a hands-on workshop, students must bring laptops. This is the 2nd part of a 2-part workshop. If you previously registered for Part 1 (1st Offering), you were automatically registered for Part 2 (1st Offering).
Abstract:
The GPT models are general-purpose language models that perform various tasks, from creating original content to writing code, summarizing text, and extracting data from documents. In this workshop, we will introduce Llama and Llama2, a collection of open-source foundation language models ranging from 7B to 70B parameters, which were released by Meta in February 2023. Llama's open-source nature provides a valuable alternative to OpenAI's ChatGPT, allowing numerous researchers and developers to use its capabilities to craft innovative tools and advance knowledge. In the first part of this workshop, we will introduce natural language processing tasks and explain why models like Llama have been introduced by the research community. The second part will demonstrate how to access and work with Llama.
Workshop Outline (Part 2):
- How to access LLama2
- How to interact with LLaMA2
- What is RAG and Fine-tuning
Prerequisites:
Basic understanding of Machine Learning – Access to provided Jupyter Notebook of LLaMA2
Link to access code - https://drive.google.com/file/d/1n_ft3GwPsncRZdjQqk2e_Aq1faCqhUwA/view?usp=sharing
Biography:
Ali Forooghi, a Ph.D. of computer science student at the University of Windsor with an interest in Natural Language Processing. (Email: foroogh@uwindsor.ca)