Generative AI and LLMs (1-day online workshop)



  • basic knowledge of Python programming.
  • basic knowledge of Machine Learning (preferred).


  • Overview of generative AI (text, images).
  • Evolution of language modeling.
  • Transformers.
  • Types of transformer-based LLMs (encoder, decoder, encoder-decoder).
  • Reinforcement learning with human feedback.
  • Overview of the most popular transformer-based LLMs (BERT, GPT, LLAMA, T5, BART…)
  • Transformer-based classification example with HuggingFace and OpenAI.
  • Prompt engineering: in-context learning, zero shot, one shot and few shot prompting, configuration parameters of the generative process
  • Full fine-tuning of large language models, parameter-efficient fine-tuning (LoRA).
  • Text generative AI evaluation (ROUGE, BLEU).
SKU: 5 Category:


This course is designed for anyone who is fascinated by the capabilities of large language models (LLMs) and generative artificial intelligence, and wants to delve into the subject a bit further, from the basic user level and beyond. We’ll use a combination of open source and paid models, to highlight differences in both.

Note: All trainings are in English language.

Additional information


January 12th, 2024, 9:00-16:00 CET (online)

Author: Pablo Maldonado

I am a consultant, technical trainer and lecturer in automation, data science and AI. My students, either at universities or companies, appreciate my hands-on approach coming from my experience at several projects across industries like financial services, marketing, and HR. Since 2017, I have been leading workshops for 30+ clients in 10+ countries including major companies such as Shell, Renault, PwC, O’Reilly Media, O2, La Poste, as well as institutions like the European Investment Bank, the Czech National Bank, the Australian Government, and many others. I have written a couple books (on Shiny, and on Deep Learning). I hold a PhD in Applied Mathematics from the Sorbonne Université in Paris, with a specialization in Game Theory and Markov Decision Processes.

Leave a Reply