From the course: RAG Fine-Tuning: Advanced Techniques for Accuracy and Model Performance
Unlock this course with a free trial
Join today to access over 24,800 courses taught by industry experts.
Using the fine-tuned model
From the course: RAG Fine-Tuning: Advanced Techniques for Accuracy and Model Performance
Using the fine-tuned model
- [Instructor] Congratulations, you have your model fine-tuned. We have raft-llama-3B, this is the model that I have fine-tuned, this is the path to the fine-tuned model, and this page contains all the details. After the fine-tuning job is completed, the model is going to show up within your profile under the models section. So I have raft-llama-3B here. And in order to use this, we'll use Hugging Face's powerful tools, and we'll learn how to generate responses using this code that they have provided. Now, before we start learning how to use this model, we'll have to make sure that we authenticate ourselves within the CoLab environment. In order to authenticate yourself, since this is a private model repository, you'll need to create an access token. In order to generate that access token, you'll have to go to settings within your profile, go to access tokens, and here you'll create new token using this button on the top right. Once you have created a new token, copy that token and…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.