Conversation bots based on Large Language Models (LLMs) have caused a massive public interest into the developments in the field of artificial intelligence. In this course, the students will learn how these models work and on which fundamental concepts they are based on. More specifically, the students will gain an understanding of the architectures and training procedures that are the building blocks of recent LLMs.
The course will contain the major concepts behind LLMs, including:
- The Attention Mechanism and Transformer Architecture
- Generative and Masked Pre-Training
- Reinforcement Learning from Human Feedback
|
LSF
– Lehre - Studium - Forschung
