AI-110 Intro to Large Language Models (LLM) and LLM based apps.

Course Description: Artificial intelligence has become an extremely important area for IT professionals and engineers in the past 10-20 years with the scientific breakthroughs and practical applications of generative AI systems, especially its Large Language Model (LLM) variant such as OpenAI’s GPT, Google’s Gemini and many other closed- and open-source models. Due to its importance and impact on every aspect of our lives, understanding the concepts, functionalities and practical usage of generative AI systems is quickly becoming essential for all IT and other technical professionals as well as for managers with technical background.

This training focuses on Large Language Models (LLMs) concepts and techniques on a high level as well as on techniques and tools of LLM application development.

Main topics:

  • Introduction to LLM based applications
  • The Foundation Technologies of LLMs (Neural Networks, Tokenizer, Transformer)
  • The 3-phase training process of LLMs (pre-training, fine-tuning, RLHF/DFO)
  • Using LLMs via APIs
  • Prompt engineering
  • Retriever Augmented Generation (RAG)
  • LangChain and LLM chains
  • LLM Agents

Besides gaining a basic understanding of the theory of Large Language Models as well as other technologies used in LLM-based applications, students will be able to examine their features and play with them during instructor’s demonstration and lab exercises.

Course Length: 8 training hours

Structure: 50% lecture, 25% demonstration by the instructor, 25% hands on lab exercises

Target audience: Technical managers as well as IT and telco professionals who want to familiarize themselves with Large Language Models and LLM based applications.

Prerequisites: Basic understanding of AI concepts, basic Python programming skills, user experience with ChatGPT or similar chatbots.