The aim of this course is to understand and deploy large language models (LLMs) from a practical perspective, enabling students to gain hands-on experience with these models without coding, using tools like Flowise and Ollama. Participants will learn how to use proprietary models like GPT-4o and open-source models like LLaMa3 for prompt engineering, creating agents, chatbots, Retrieval-Augmented Generation (RAG) models, and other NLP applications. Additionally, non-generative tasks such as document classification (sentiment analysis) and information retrieval will be covered. The course will also include multimodal models that incorporate speech or images. Finally, students will learn how to evaluate the deployed models to assess their accuracy and effectiveness.

The course will emphasize ethical considerations, including addressing bias in language, and responsibly handling sensitive information.

The course is part of the NLP master hosted by the Ixa NLP research group at the HiTZ research center of the University of the Basque Country (UPV/EHU).

Student profile

This course is targeted at graduate students and professionals from various disciplines (linguistics, journalism, computer science, sociology, etc.) who need to understand and deploy LLMs easily. The goal is to provide participants with the autonomy to solve practical problems by understanding and deploying LLM-based applications in diverse and creative ways. No coding skills are necessary for the practical content, the OpenAI ChatGPT Plus subscription plan is recommended to complete some of the labs. While previous attendance to the other courses might be useful, it is not required.

Contents

Introduction to LLMs

What is a LLM?
How do they behave?
Prompting
LABORATORY: Basic Prompt Engineering

Advance Prompting and non Generative tasks

Reasoning: Chain of Thought & Self Consistency
Document Classification
Information Retrieval
LABORATORY: Advance Prompt Engineering
LABORATORY: Document Classification & Information Retrieval

ChatBots and Retrieval Augmented Generation

Conversational models
RAG Including external or private knowledge into LLMs
LABORATORY: ChatBots and RAG

Multimodal LLMs and Agents

Text + Images + Speech
Multimodal Search
Reasoning: Agents & Multi Agents
LABORATORY: Including voice and images into LLMs
LABORATORY: Agents

Evaluation

Hallucinations
Automatic and quantitative evaluation of LLMs
LABORATORY: Evaluation of LLMs

Instructors

Person 2

Ander Barrena

Assistant Professor at IXA
and HiTZ

Practical details

General information

Part of the Language Analysis and Processing master program.
  • The classes will be broadcasted live online. The practical labs will be also held online.
  • 5 theoretical sessions with interleaved hands-on labs (20 hours).
  • The content of the course is subject to change.
  • Scheduled from October 14th to 18th 2024, 15:00-19:00 CET.
  • Teaching language: English.
  • Capacity: 60 attendants (First-come first-served).
  • Cost: 270€ + 4€ insurance = 274€
    (If you are an UPV/EHU member or have already registered for another course, it is 270€).

Registration

Pre-registration is open now.
  • Please register by email to ixa.administratzailea@ehu.eus (subject "Registration to gpLLMme", please CC olatz.arregi@ehu.eus).
  • After you receive the payment instructions you will have three days to formalize the payment.
  • Plese use the same email for any enquiry you might have.
  • The university provides official certificates for an additional fee. Please apply AFTER completing the course.
  • The university can provide invoices addressed to universities or companies. More details are provided after registration is made.

Prerequisite
No coding skills are necessary for the practical content, the OpenAI ChatGPT Plus subscription plan is recommended to complete some of the labs. While previous attendance to the other courses might be useful, it is not required.