AI-413 Open-source LLM Application Developer
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 deep learning and more recently of generative AI systems, especially with its Large Language Model (LLM) variant such as OpenAI’s ChatGPT and Google’s Bard. Due to its importance and impact on every aspect of our lives, understanding the concepts, functionalities and practical usage of 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) and teaches participants the following topics (preliminary version):
- The Foundations: Neural Networks, Deep Learning, CNN, RNN, Transfer Learning, NLP
- “Attention is all you need” – The Transformer Architecture
- Pre-training of LLMs
- LLM Fine-tuning techniques: Prompt Tuning and Parameter Efficient Fine Tuning (PEFT)
- Reinforcement Learning with Human feedback (RLHF)
- Text Embeddings and Searching with Vector Databases
- Using LLMs in Applications
- MLOps, LLMOps (optional)
- Ethical considerations (optional)
Besides gaining a basic understanding of the theory of Large Language Models (LLMs) models, students will also make extensive lab exercises using the Python based TensorFlow or PyTorch deep learning framework with the Hugging Face ecosystem.
Course Length: 24 training hours
Structure: 50% theory, 50% hands on lab exercises
Target audience: All types of IT, telecom, and other technical professionals as well as managers with technical background who want to understand the basic concepts, functionalities, and practical usage of Large Language Models (LLMs).
Prerequisites: Basic understanding of AI, Machine Learning and Deep Learning concepts. Basic Python programming skills. Some experience in using TensorFlow or PyTorch deep-learning frameworks.
Suggested preliminary course: AI-202 Deep Learning Basics