Fine-Tune Your LLMs
1h 14mAdvanced2024-04-18
Authors
Kesha Williams
Software Engineering Manager, Speaker, Tech Blogger
Course details
In this course, award-winning tech innovator and AI/ML leader Kesha Williams guides you through several concepts and techniques that you can use to fine-tune LLMs using your own data. Explore the concepts and costs of fine-tuning and learn how to set up your environment for it. Go over the steps to prepare your data and fine-tune a pre-trained LLM. Plus, practice evaluating and iterating a fine-tuned model. Practical, hands-on challenges in each chapter give you a chance to deepen your understanding of the topics.
Skills covered
JupyterNatural Language Processing (NLP)PythonArtificial Intelligence (AI)Open SourceOne-Off
Concepts
Introduction
- Introduction to fine-tuning LLMs
- Review the fine-tuning project
Exploring Concepts and Costs of Fine-Tuning
- Explore LLMs
- Review the fine-tuning process
- Understand the costs of fine-tuning
Setting up Your Environment for Fine-Tuning
- Explore the OpenAI API for fine-tuning
- Use GitHub codespaces
- Sign up for an OpenAI account
Preparing Data for Fine-Tuning
- Source data for fine-tuning
- Challenge - Source data for fine-tuning
- Solution - Source data for fine-tuning
- Prepare data for fine-tuning
- Challenge - Prepare and upload data for fine-tuning
- Solution - Prepare and upload data for fine-tuning
Fine-Tuning a Pretrained LLM
- Train a new fine-tuned model
- Challenge - Fine-tune a pretrained LLM
- Solution - Fine-tune a pretrained LLM
- Retrieve and use a fine-tuned model
- Challenge - Develop a chatbot based on a fine-tuned model
- Solution - Develop a chatbot based on a fine-tuned model
Evaluating a Fine-Tuned Model
- Evaluate a fine-tuned model
- Iterate a fine-tuned model
- Challenge - Evaluate a fine-tuned model
- Solution - Evaluate a fine-tuned model
Conclusion
- Your fine-tuning journey