From the course: Fine-Tune Your LLMs
Join today to access over 23,000 courses taught by industry experts.
Review the fine-tuning process
From the course: Fine-Tune Your LLMs
Review the fine-tuning process
- [Narrator] You could teach an AI to write poetry like Emily Dickinson, code like a Silicon Valley wizard, or even chat like your best friend. Welcome to the world of fine tuning. Fine tuning starts with a foundation model like GPT in which you give focused training to help it get really good at a specific task. As you learned in the last lesson, ChatGPT is a fine tuned version of GPT. Let's start with why you would want to fine tune. Fine tuning improves the overall performance of a model for your particular use case. Specifically, the responses to your prompts are improved when using a fine tuned model. You can reduce token costs because your prompts are shorter and require fewer examples than few shot prompting or retrieval augmented generation or RAG, and the model responds to your queries or prompts faster with lower latency. So what does the fine tuning process look like? Start with obtaining training data to your specific use case. For the project we're building, the dataset…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.