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 and open-source models like Gemma, DeepSeek or Qwen for prompt engineering, creating agents, chatbots, Retrieval-Augmented Generation (RAG) models, and other NLP applications. Additionally, non-generative tasks such as information retrieval will be covered. The course will also include multimodal models that incorporate 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 by local models.

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 required for the practical content, but basic installation skills and admin permissions are necessary. While previous attendance to the other courses might be useful, it is not required.

Contents

Introduction to LLMs

What is a LLM? Language Modeling Task
Neural Networks, Vector Representations and Deep Learning
Pre-Trained Models - GPT3 and LLaMa
shortLab1: Zero, one and few shot with oLLaMa
Intruction Tuning and RLHF
shortLab2: Basic Prompting
flowiseLab1: warmUp and basic prompting with huggingface and oLLama models

Advance Prompting

Cost and Environmental impact of LLMs
System prompts
shortLab3: system prompts with oLLama
Reasoning
Chain of Thought
Tree of Thoughts
Self Consistency
shortLab4: advance prompting with oLLama
flowiseLab2: simple LLM chains and prompt chaining

ChatBots and Retrieval Augmented Generation

Conversational models
Hallucinations
shortLab5: hallucinations with oLLama
Information Retrieval
Vector Databases
shortLab6: contextual grounding
Retrieval Augmented Generation
flowiseLab3: retrieval augmented generation

Multimodal LLMs and Agents

Image Captioning and Image Generation
Difusion Models
shortLab7: image caption and image generation with DALL-E
Agents and Tools
Sequential Agents
Multi Agents
shortLab8: agents with oLLama
flowiseLab4: Sequential and Multi Agents

Safety and Evaluation

Local Models, APIs and Proprietary models
LLM bias and keeping the user safe
shortLab9: LLM bias and safe models
Human and Automatic Evaluation
Proxy Tasks
LLM as judges
shortLab10: LLMs as judges and proxy tasks with oLLama
flowiseLab5: Agents and Evaluation of LLMs

Instructors

Person 1

Ander Barrena

Assistant Professor member of 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 June 29th to July 3rd 2026/, 15:00-19:00 CET.
  • Teaching language: English.
  • Capacity: 70 attendants (First-come first-served).
  • Cost: 400€ + 4€ insurance = 404€
    (If you are an UPV/EHU member or have already registered for another course, it is 400€).

Registration

If you are interested in any of the courses, Fill out the form