Generative AI Engineering and Fine-Tuning Transformers

Overview

Class Central Tips

The demand for technical gen AI skills is exploding. Businesses are hunting hard for AI engineers who can work with large language models (LLMs). This Generative AI Engineering and Fine-Tuning Transformers course builds job-ready skills that will power your AI career forward. During this course, you’ll explore transformers, model frameworks, and platforms such as Hugging Face and PyTorch. You’ll begin with a general framework for optimizing LLMs and quickly move on to fine-tuning generative AI models. Plus, you’ll learn about parameter-efficient fine-tuning (PEFT), low-rank adaptation (LoRA), quantized low-rank adaptation (QLoRA), and prompting. Additionally, you’ll get valuable hands-on experience in online labs that you can talk about in interviews, including loading, pretraining, and fine-tuning models with Hugging Face and PyTorch. If you’re keen to take your AI career to the next level and boost your resume with in-demand gen AI competencies that catch the eye of an employer, ENROLL today and have job-ready skills you can use straight away within a week!

Syllabus

Transformers and Fine-Tuning

In this module, you will be introduced to Fine Tuning. You’ll get an overview of generative models and compare Hugging Face and PyTorch frameworks. You’ll also gain insights into model quantization and learn to use pre-trained transformers and then fine-tune them using Hugging Face and PyTorch.

Parameter Efficient Fine-Tuning (PEFT)

In this module, you will gain knowledge about parameter efficient fine-tuning (PEFT) and also learn about adapters such as LoRA (Low-Rank Adaptation) and QLoRA (Quantized Low-Rank Adaptation). In hands-on labs you will train a base model and pre-train LLMs with Hugging Face.