Class is in session

Fine-Tuning Open-Source LLMs

5 Weeks


Cohort-based Course

Achieve optimal performance from your fine-tuned LLM

Previously at

South Park Commons

Course overview

Fine-tuning that *actually* works

A properly fine-tuned LLM can achieve performance that outshines GPT-4. However, achieving these results is not as simple as making an OpenAI API call. In this course, we'll demystify fine-tuning by systematically going step-by-step through the entire process.

Step 1: Curate Data

Step 2: Train Model

Step 3: Evaluate Results

Step 4: Apply Guardrails

Step 5: Deploy Model

Step 6: Improve Results

For each step, I will provide proven strategies and real-world case studies from my experience as an AI consultant.

When it comes to fine-tuning, the devil is in the details. Practitioners must be precise and exacting to reach peak performance. I will provide hands-on help so that students successfully build an end-to-end fine-tuning solution during the course project.

Who is this course for


You want to evaluate whether fine-tuning would be beneficial for your company


You want to enhance your expertise as a software engineer or data scientist


You want to explore the world of open-source LLMs

What you’ll get out of this course

Explore Open-Source LLMs

Identify the pros and cons of various open-source LLMs (Llama, Mistral, etc.), and determine when to use one.

Analyze the current state of open-source LLMs and where they are likely to go in the future.

Curate High-Quality Data

Create a fine-tuning dataset that is ideal for your use case.

Adjust your dataset to handle nuances and edge cases.

Train a Model

Apply the QLoRA algorithm to fine-tune a model (and understand what's actually happening under the hood!).

Conduct hyperparameter tuning to optimize training for your use case.

Evaluate Results

Design a test suite to systematically evaluate model results.

Identify weaknesses in your model and determine how to fix them.

Optimize Costs and Scale

Deploy your model using techniques such as quantization to reduce costs.

Optimize inference parameters for your use case.

Continuous Improvement

Analyze the production impact of your model.

Implement a feedback system to continuously improve results.

This course includes

8 interactive live sessions

Lifetime access to course materials

15 in-depth lessons

Direct access to instructor

5 projects to apply learnings

Guided feedback & reflection

Private community of peers

Course certificate upon completion

Maven Satisfaction Guarantee

This course is backed by Maven’s guarantee. You can receive a full refund within 14 days after the course ends, provided you meet the completion criteria in our refund policy.

Course syllabus

Expand all modules
  • Week 1

    Jun 12—Jun 16

    Week dates are set to instructor's time zone


    • Jun


      Fine-Tuning Basics

      Wed, Jun 12, 6:00 PM - 7:30 PM UTC

    • Jun


      Week 1 Office Hours

      Fri, Jun 14, 6:00 PM - 7:00 PM UTC


    • Fine-Tuning Basics

  • Week 2

    Jun 17—Jun 23

    Week dates are set to instructor's time zone


    • Jun


      Train Your Model

      Wed, Jun 19, 6:00 PM - 7:30 PM UTC

    • Jun


      Week 2 Office Hours

      Fri, Jun 21, 6:00 PM - 7:00 PM UTC


    • Train Your Model

  • Week 3

    Jun 24—Jun 30

    Week dates are set to instructor's time zone


    • Jun


      Optimize Your Dataset

      Wed, Jun 26, 6:00 PM - 7:30 PM UTC

    • Jun


      Week 3 Office Hours

      Fri, Jun 28, 6:00 PM - 7:00 PM UTC


    • Optimize Your Dataset

  • Week 4

    Jul 1—Jul 7

    Week dates are set to instructor's time zone

    Nothing scheduled for this week.

  • Week 5

    Jul 8—Jul 12

    Week dates are set to instructor's time zone


    • Jul


      Deploy Your Model

      Wed, Jul 10, 6:00 PM - 7:30 PM UTC

    • Jul


      Week 4 Office Hours

      Fri, Jul 12, 6:00 PM - 7:00 PM UTC


    • Deploy Your Model

  • Post-Course


    • Private Coaching Session

What students are saying

        This course immediately pays for itself! I was able to apply many of the lessons learned to my own fine-tuning project, and saw significant improvement. Scott does an amazing job of making complex topics easy to understand, while providing specific and detailed advice.
Haard Shah

Haard Shah

Data Scientist, 7 Cups
        Taking this course provided me with a strong understanding of the entire fine-tuning process. I was able to create my own fine-tuned model after just a few days of working with Scott, and my startup now has a roadmap for how to continuously improve our model over time.
Scott Morris

Scott Morris

Co-Founder/CTO, Limo Health
Free resource

7 Cups Increases Engagement 250% Through Fine-Tuning

Discover how 7 Cups fine-tuned an LLM to create an AI therapist that is 250% more engaging than leading proprietary LLMs.

Get the free case study

Meet your instructor

Scott Kramer

Scott Kramer

I've led AI at startups across every stage, from founding engineer through IPO (3 out of 3 successful exits).

After my last exit, I became a solopreneur and specialize in helping companies fine-tune LLMs.

This course is a culmination of my learnings from successfully fine-tuning LLMs for clients.

A pattern of wavy dots
Be the first to know about upcoming cohorts

Fine-Tuning Open-Source LLMs


Bulk purchases

Course schedule

4-6 hours per week
  • Wednesday Workshops

    2:00pm - 3:30pm EST

    Students will explore each module, investigate real-world case studies, and identify strategies to apply to their project.

  • Friday Office Hours (Optional)

    2:00pm - 3:00pm EST

    Students will receive hands-on help with their fine-tuning projects.

  • Private Coaching Session

    1 hour

    Each student will receive one private coaching session to review their project in depth and ensure they achieve optimal results.

  • Weekly projects

    2 hours per week

    Students will design and implement a fine-tuning use case based on their interests.

    Each week, students will apply strategies learned during the workshop to improve their results.

    This isn't just some toy project - students will be building a model with actual data.

Learning is better with cohorts

Learning is better with cohorts

Active hands-on learning

This course builds on live workshops and hands-on projects

Interactive and project-based

You’ll be interacting with other learners through breakout rooms and project teams

Learn with a cohort of peers

Join a community of like-minded people who want to learn and grow alongside you

Frequently Asked Questions

What happens if I can’t make a live session?
I work full-time, what is the expected time commitment?
What’s the refund policy?
Can I get a group discount?
What are the prerequisites?

Stay in the loop

Sign up to be the first to know about course updates.

A pattern of wavy dots
Be the first to know about upcoming cohorts

Fine-Tuning Open-Source LLMs


Bulk purchases