Intermediate1h35m

Finetuning Large Language Models

Instructor: Sharon Zhou

Earn an accomplishment with PRO · Updated Oct 7, 2025

Enroll for Free

Intermediate
1h35m
9 Video Lessons
6 Code Examples
1 Graded Assignment PRO
Earn an accomplishment with PRO
Updated Oct 7, 2025
Instructor: Sharon Zhou
AMD, formerly Lamini
Learn more aboutMembership PRO Plan

Enroll for Free

What you'll learn

Learn the fundamentals of finetuning a large language model (LLM).
Understand how finetuning differs from prompt engineering, and when to use both.
Get practical experience with real data sets, and how to use techniques for your own projects.

Course recap

PRO

Taught by Sharon Zhou (CEO of Lamini), this course covers when and how to fine-tune LLMs on your own data. It compares fine-tuning to prompt engineering, explains instruction fine-tuning (the technique that turned GPT-3 into ChatGPT), and walks through the complete fine-tuning process: data preparation, training, and evaluation.

Concept map

Key concepts

Fine-TuningSpecializing general-purpose models (like turning GPT-3 into ChatGPT) by training on task-specific data
Instruction fine-tuningTeaching LLMs to follow instructions, the key technique behind chat models
Fine-tuning vs promptingPrompting is great for prototyping with no data; fine-tuning excels for enterprise/production use with more data and consistency requirements
LoRA (Low-Rank Adaptation)Parameter-efficient fine-tuning that reduces trainable parameters by 10,000x (GPT-3 example), requiring 3x less GPU memory
Catastrophic forgettingRisk of losing general capabilities when fine-tuning on narrow tasks

Lesson highlights

1.Introduction — Course overview, fine-tuning as a tool alongside prompt engineering
2.Why finetune — Comparing fine-tuned vs base models (Llama 2 demo), benefits for performance, privacy, cost, latency
3.Where finetuning fits in — Fine-tuning in the broader training pipeline, pre-training vs fine-tuning
4.Instruction finetuning — How instruction tuning works, data formats, chat-style fine-tuning
5.Data preparation — Preparing and structuring data for fine-tuning, prompt templates
6.Training process — The actual fine-tuning training loop, hyperparameters
7.Evaluation and iteration — Evaluating fine-tuned models, iterating on results
8.Considerations on getting started — Practical tips, task complexity vs model size, compute requirements, LoRA/PEFT
9.Conclusion — Summary and next steps

About this course

Join our new short course, Finetuning Large Language Models! Learn from Sharon Zhou, Vice President of Artificial Intelligence at AMD, and instructor for the GANs Specialization and How Diffusion Models Work.

When you complete this course, you will be able to:

Understand when to apply finetuning on LLMs
Prepare your data for finetuning
Train and evaluate an LLM on your data

With finetuning, you’re able to take your own data to train the model on it, and update the weights of the neural nets in the LLM, changing the model compared to other methods like prompt engineering and Retrieval Augmented Generation. Finetuning allows the model to learn style, form, and can update the model with new knowledge to improve results.

Who should join?

Learners who want to understand the techniques and applications of finetuning, with Python familiarity, and an understanding of a deep learning framework such as PyTorch.