Begin your journey with Large Language Models (LLMs) by understanding what they are and what they can do, and peek under the hood to get an idea of how they work!

Introduction to large language models (LLMs)

Using a pipeline for summarization

Cleaning up replies

Using pre-trained LLMs

Generating text

Translating text

Understanding the transformer

Identify the transformer

Using the correct model structure

Getting Started with Large Language Models (LLMs)

Learn how to leverage pre-trained LLMs and datasets from Hugging Face to fine-tune a model.

Preparing for fine-tuning

Tokenizing text

Mapping tokenization

Fine-tuning through training

Setting up training arguments

Setting up the trainer

Using the fine-tuned model

Fine-tuning approaches

Transfer learning with one-shot learning

Transfer learning approaches

Fine-tuning LLMs

Dive into different metrics to assess model performance and wrap up by learning about the challenges of applying LLMs in the real world.

The evaluate library

Loading metrics with evaluate

Describing metrics

Using evaluate metrics

Metrics for language tasks: perplexity and BLEU

Evaluating perplexity

BLEU translations

Metrics for language tasks: ROUGE, METEOR, EM

Evaluating with ROUGE

Evaluating with METEOR

Evaluating with EM

Safeguarding LLMs

Checking toxicity

Evaluating regard

The finish line

Evaluating LLM performance

Course Glossary Introduction to LLMs in Python

Large Language Models (LLMs) have become pivotal tools driving some of the most stunning advancements and applications in today's AI landscape. This hands-on course will equip you with the practical knowledge and skills needed to understand, build, and harness the power of LLMs for solving complex language tasks such as translation, language generation, question-answering, and more. Through iteractive coding exercises, you will learn to work with transformers. You'll also explore pre-trained language models and datasets from Hugging Face. By the end of this course, you will be able to fine-tune and evaluate pre-trained LLMs using specialized metrics. You will also gain an understanding of the key challenges and ethical considerations of enabling real-world LLM applications.

The videos contain live transcripts you can reveal by clicking "Show transcript" at the bottom left of the videos.
The course glossary can be found on the right in the resources section.
To obtain CPE credits you need to complete the course and reach a score of 70% on the qualified assessment. You can navigate to the assessment by clicking on the CPE credits callout on the right.

<h2>Uncover What's Behind the Large Language Models Hype</h2>
<br><br>
Large Language Models (LLMs) have become pivotal tools driving some of the most stunning advancements and applications in today's AI landscape. This hands-on course will equip you with the practical knowledge and skills needed to understand, build, and harness the power of LLMs for solving complex language tasks such as translation, language generation, and more.
<br><br>
<h2>Discover LLM Architecture and Leverage Pre-Trained Models</h2>
<br><br>
Through interactive coding exercises, you'll discover different transformer architectures and how to identify them. You'll explore leveraging pre-trained language models and datasets from Hugging Face for fine-tuning and evaluating your model using advanced metrics that fit LLMs. Finally, you'll find out more about ethical and bias concerns relevant to LLMs and ways to identify these. By the end of this course, you will be able to build LLMs, fine-tune, and evaluate them using specialized metrics while understanding the key challenges and ethical considerations of enabling real-world LLM applications.

Working with Hugging Face

Learn the nuts and bolts of LLMs and the revolutionary transformer architecture they are based on!

Evaluating with ROUGE

Introduction to LLMs in Python

Istruzioni dell'esercizio

Esercizio pratico interattivo