At a Glance

Name: Fine-tune an LLM with Hugging Face using LoRA and QLoRA
Price: Free CAD
Rating: 4.7 (14 reviews)
Author: wojciech_fulmyk, fateme_akbari, joseph_santarcangelo

Perform parameter-efficient fine-tuning (PEFT) using LoRA and QLoRA with Hugging Face! This hands-on project ensures you master crucial concepts quickly, getting you up and running on Hugging Face in no time. If you want to adapt Hugging Face models for your task, this hands-on project is for you!

A look at the project ahead

Hugging Face is often referred to as "the GitHub of AI models" due to the vast collection of models available in its repositories. The simplicity of loading and utilizing AI models from Hugging Face significantly reduces the complexity of using and implementing large language models. In this hands-on project, you will acquire the skills to fine-tune a BERT-based language model for a specific task. The project encompasses parameter-efficient fine-tuning (PEFT) methods, including LoRA and QLoRA.

Learning objectives

Upon completion of this project, you can:

Load and predict using models from Hugging Face
Fine-tune language models using LoRA
Fine-tune language models using QLoRA
Understand the advantages and disadvantages of LoRA and QLoRA

What you'll need

For this project, you need an intermediate level of proficiency in Python, PyTorch, and deep learning. Additionally, the only equipment you need is a computer equipped with a modern browser, such as the latest versions of Chrome, Edge, Firefox, or Safari.

Offered By: IBMSkillsNetwork

Fine-tune an LLM with Hugging Face using LoRA and QLoRA

At a Glance

A look at the project ahead

Learning objectives

What you'll need