What you'll learn
- Understand what LLM hyperparameters control
- Adjust temperature for focused or creative outputs
- Use Top P to shape token selection
- Reduce repetition with frequency penalties
- Encourage variety with presence penalties
- Set stop sequences to control response endings
- Navigate and configure an LLM playground
- Choose settings for different prompting goals
Getting useful results from an LLM isn't just about writing a better prompt. The settings behind that prompt matter too.
This course introduces the hyperparameters that influence how language models generate responses, giving you a clearer picture of what happens when you change them.
You'll explore temperature and Top P, see how frequency and presence penalties affect repetition and variety, and learn how stop sequences can give you more control over where an output ends.
The goal is simple: less guessing. More intentional experimentation. By understanding what each control does, you'll be better equipped to tune LLM responses for different tasks and build stronger practical prompt engineering skills.
I'm a proud lifetime ZTM member. It's changed the trajectory of my life. The projects I built from ZTM courses made me stand out as the #1 candidate and landed me the job. Thanks to Andrei, Yihua, and the entire ZTM team, instructors, and community.
Who You Will Learn With
You're getting more than just a course
Our instructors, TAs, Mentors, Alumni, and fellow students go above and beyond to help guide you and ensure you're on the right path to achieve your goals. Our private ZTM Discord server is a key factor in taking your skills, confidence and career to the next level.
