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 25,200 courses taught by industry experts.

Fine-tuning the Llama 3.2 model on Hugging Face

Fine-tuning the Llama 3.2 model on Hugging Face

From the course: RAG Fine-Tuning: Advanced Techniques for Accuracy and Model Performance

Start my 1-month free trial Buy for my team

Fine-tuning the Llama 3.2 model on Hugging Face

“

- [Instructor] It's time to fine-tune our large language model using our prepared data set. We'll be fine-tuning Llama 3.2 3 billion model. So let's quickly search for that model on Hugging Face. And the third one that you see, Llama 3.2 3 billion Instruct, this is the model that we will be fine-tuning. Clicking on it opens up the model card where you'll find all the information about this model. Important thing is that you will not be able to use this model unless you have requested access to use that means to download or to fine-tune this model. So when you'll open this page up for the first time, it'll ask you to first of all log in or sign up. Once you log in, you'll have to request access to this model. It takes around 10 minutes to get your request approved by the Meta team. And once that is done, you'll be able to fine-tune the model or use the model. On the top right, you have the train button. So clicking on this train dropdown, it gives you three options to fine-tune your…

Contents