From the course: Introduction to Prompt Engineering for Generative AI
Join today to access over 25,300 courses taught by industry experts.
Model fine-tuning
From the course: Introduction to Prompt Engineering for Generative AI
Model fine-tuning
- [Narrator] In this one, we're going to talk about fine-tuning. What fine-tuning allows us to do is to take a model, say a language model, and add some training to it in order to make it extremely good and efficient in a specific task. So say we have a company that helps programmers write code, we can come up with a data set or a lot of examples of prompts and completions. We make sure these examples are extremely high as far as quality goes. Then we can fine tune a model in order to make it very good at helping programmers write some code. What's great about fine-tuning is that when done right, it can help you get more out of models. As a result, you can use smaller models and gain efficiency. Fine-tuning can also help you save up on tokens because you don't have to construct a very long prompt to instruct the model on what to do. Now, the process itself of fine-tuning a model can cost a little bit, but it may pay off in the long run. Now, this process is not in the scope of our…
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.