.png&w=1536&q=75)
Fine-Tuning LLMs
Achieve optimal performance from your fine-tuned LLM.
This course is no longer available.
Explore other coursesPrevious Clients Include
Course overview
Fine-tuning that *actually* works
A properly fine-tuned LLM can achieve performance that outshines leading foundation models. However, achieving these results is not as simple as making an 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
01
Software engineers and data scientists who have dabbled with LLMs and are considering a career switch to AI.
02
AI and ML engineers who want to enhance their skillset.
03
Startups who are evaluating whether fine-tuning would be beneficial for their company.
What you’ll get out of this course
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.
Build a Data Flywheel
Analyze the production impact of your model.
Implement a process to continuously improve results.
Explore Open-Source LLMs
Identify the pros and cons of various open-source LLMs and evaluate how their performance compares to the leading proprietary models.
Analyze the current state of LLMs and where they are likely to go in the future.
What’s included
Live sessions
Learn directly from Scott Kramer in a real-time, interactive format.
Lifetime access
Go back to course content and recordings whenever you need to.
Community of peers
Stay accountable and share insights with like-minded professionals.
Certificate of completion
Share your new skills with your employer or on LinkedIn.
Maven Guarantee
This course is backed by the Maven Guarantee. Students are eligible for a full refund up until the halfway point of the course.
Course syllabus
5 live sessions • 31 lessons • 7 projects
Week 1
- 📄
Course Overview
- ✍️
Introduce Yourself
Submit by Nov 6 - ✍️
Create a Fireworks Account
Submit by Nov 9 - 📄
LLM Fundamentals
- 📄
Open-Source LLMs
- 📄
Prompt Engineering
- 📄
Improving LLM Responses
- 📄
Fine-Tuning Archetypes
- 📄
The Fine-Tuning Process
- ✍️
Choose Your Course Project
Submit by Nov 12 - ✍️
Prompt Engineering
Submit by Nov 12
Welcome! Let's Get Started
Welcome to Fine-Tuning LLMs! Go through these lessons to learn a little more about what's to come, get some of your questions answered, and introduce yourself to the rest of the cohort.
Never Fine-Tune Before You Do These Things!
Review LLM best practices and identity when (and when not) to fine-tune.
Fine-Tuning Basics
Traverse each stage of the fine-tuning process, explore real-world examples, and evaluate model options.
Nov
5
Q&A Session 1
Week 2
- 📄
Background
- 📄
Parameter Efficient Fine-Tuning
- 📄
QLoRA Algorithm
- 📄
QLoRA Hyperparameter Tuning
- 📄
QLoRA Implementation
- 📄
Training Evaluation
- 📄
Training Demo
- 📄
RLHF (Optional)
- ✍️
Fine-Tune Your First Model
Submit by Nov 19
Train Your Model
Apply fine-tuning algorithms, optimize hyperparameters, and analyze results.
Nov
12
Q&A Session 2
Week 3
- 📄
Evaluation Methods
- 📄
Create a Test Suite
- 📄
Post-Deployment Evaluation
- 📄
Demo
- ✍️
Create Your Own Evaluation Framework
Submit by Nov 30 - 📄
The Importance of Dataset Quality
- 📄
Improving Synthetic Data
- 📄
How Large of a Dataset Do I Need?
- 📄
Real World Case Studies
- 📄
Improving Poetry Generation
- ✍️
Improve Results
Submit by Nov 29
Evaluation Frameworks
Creating a robust evaluation framework is essential to assessing the quality of an LLM... fine-tuned or not!
Dataset Improvement Strategies
The secret to fine-tuning is to have really, really, ridiculously good looking data. And in this module, you'll discover what that entails.
Nov
19
Q&A Session 3
Week 4
- 📄
Deployment Options
- 📄
Quantization
- 📄
Inference Parameters
- 📄
Incorporating User Feedback
- 📄
Add Guardrails
- 📄
(Optional): End-to-End Fine-Tuning Walkthrough
Deploy Your Model
Nov
29
Q&A Session 4
Week 5
Dec
3
Q&A Session 5
Bonus
- 📄
Schedule Your Session
Private Coaching Session
Each student will schedule a one hour private coaching session to discuss strategy, review progress, and receive feedback on their course project.
What students are saying
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.
Course schedule
4-6 hours per week
Self-Paced Lessons
2 hours per week
1-2 modules per week with lessons walking you through the step-by-step process of fine-tuning an LLM. Each module includes recorded demo videos, coding examples, and additional resources to help you complete the next project.
Course Project
2 hours per week
Students will design and implement a fine-tuned model of their choosing. Each week, students will apply strategies from the lessons to further improve their model.
Q&A with Scott
1 hour per week
Live Q&A calls with Scott and the rest of the cohort to answer questions and receive hands-on help with that week's projects.
Private Coaching Session
1 hour session
Each student will receive a live coaching session with Scott to review their project, receive personalized feedback, and discuss how to improve their AI skills further.
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