Getting to know Llama (your own ChatGPT)
Presenter: Ali Forooghi
Date: Monday, January 29, 2024
Time: 12:30 pm – 1:30 pm
Location: 4th Floor (Workshop space) at 300 Ouellette Avenue (School of Computer Science Advanced Computing Hub)
Abstract:
The GPT models are general-purpose language models that can perform a broad range of 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 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 in crafting innovative tools and advancing knowledge. In this workshop, we will delve deeply into these models, exploring their use cases, discussing their limitations, and observing their live performance.
Workshop Outline:
Introduction to Large Language Models
Understanding different models
What is LLama
How to access Llama2
RAG (Retrieval Augmented Generation)
Fine-Tuning Prerequisites: Basic understanding of NLP and Deep Learning – Basic Python skills
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)