Large Language Models (LLMs) represent the current pinnacle of AI technology, driving remarkable advancements in Natural Language Processing and Understanding. This chapter serves as your gateway to comprehending LLMs: what they are, their remarkable capabilities, and the wide array of language tasks they excel at. You'll gain practical experience in loading and harnessing various LLMs for both language understanding and generation tasks. Along the way, you'll be introduced to the successful catalyst at the heart of most LLMs: the transformer architecture. Ready to start this journey into the world of LLMs?

Introducing large language models

Classifying a restaurant's customer review

LLM for sentiment classification

Pipeline re-arrangement puzzle

Tasks LLMs can perform

Using a pipeline for summarization

Time for some question-answering!

The transformer architecture

Hello PyTorch transformer

Hands-on translation pipeline

Generating replies to customer reviews

The Large Language Models (LLMs) Landscape

In this chapter, you'll uncover the secrets and practical intricacies of transformers, the most popular deep learning architecture used to create today's most successful Language Models. Step by step, and aided by the PyTorch library, you'll learn how to manually design and configure different types of transformer architectures. You'll develop a strong understanding of their core elements, including self-attention mechanisms, encoder and decoder layers, and specialized model heads designed for specific language tasks and use cases.

Attention mechanisms and positional encoding

Hands-on positional encoding

Why do we need positional encoding?

Multi-headed self attention

Setting up a multi-headed attention class

Implementing multi-headed self-attention

Building an encoder transformer

Post-attention feed-forward layer

Time for an encoder layer

Encoder transformer body and head

Testing the encoder transformer

Building a decoder transformer

Building a decoder body and head

Testing the decoder transformer

Building an encoder-decoder transformer

Incorporating cross-attention in a decoder

Trying out an encoder-decoder transformer

Transformer assembly bottom-up

Building a Transformer Architecture

This chapter unveils the transformative potential of harnessing pre-trained Large Language Models (LLMs). Throughout the chapter, you'll discover effective tips and tricks for mastering intricate language use cases and gain practical insights into leveraging pre-trained LLMs and datasets from Hugging Face. Along the way, you will learn the ins and outs of several common language problems, including sentiment classification to summarization to question-answering, and explore how LLMs are adaptively trained to solve them.

LLMs for text classification and generation

Pipelines vs auto classes

Classifying two movie opinions

Tidying up a text generation use case

LLMs for text summarization and translation

Summarizing a product opinion

The Spanish phrasebook mission

LLMs for question answering

Load and inspect a QA dataset

Extract and decode the answer

LLM fine-tuning and transfer learning

Fine-tuning preparations

The inside-out LLM

Matching LLM use cases and architectures

Harnessing Pre-trained LLMs

Our exciting LLMs learning journey is approaching its end! You'll delve into different metrics and methods to assess how well your model is performing, whether it's a pre-trained one, a fine-tuned version, or something you've built from the ground up! You'll learn about the crucial aspects and challenges of applying Language Models in real-world scenarios, including optimizing a model with feedback from humans (RLHF), tackling biased language outputs, and more.

Guidelines and standard metrics for evaluating LLMs

Calculating accuracy

Beyond accuracy: describing metrics

Beyond accuracy: using metrics

Specialized metrics for language tasks

Perplexed about 2030

A feast of LLM metrics

BLEU-proof translations

Model fine-tuning using human feedback

The role of a reward model

Setting up an RLHF loop

Challenges and ethical considerations

Toxic employee reviews?

Best "regard"!

The finish line

Evaluating and Leveraging LLMs in the Real World

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, the most popular deep-learning architecture for constructing LLMs and NLP systems. You'll also explore pre-trained language models and datasets from Hugging Face: a vast repository of resources for seamlessly integrating LLMs into your projects. By the end of this course, you will be able to build LLMs using various transformer architectures and configure, fine-tune, and evaluate pre-trained LLMs using specialized metrics. You will also gain insights into advanced concepts like Reinforcement Learning from Human Feedback (RLHF) and understand the key challenges and ethical considerations of enabling real-world LLM applications.

<h2>Uncover What's Behind the Large Language Models Hype</h2>
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.<br><br>
<h2>Design your Own LLM Architecture and Leverage Pre-Trained Models</h2>
Through iteractive coding exercises, we will demystify transformers, the most popular deep-learning architecture for constructing LLMs and NLP systems. We'll also explore pre-trained language models and datasets from Hugging Face: a vast collection of resources for seamlessly integrating LLMs into your projects. By the end of this course, you will be able to build LLMs using various transformer architectures and configure, fine-tune, and evaluate pre-trained LLMs using specialized metrics. You will also gain insights into advanced concepts like Reinforcement Learning from Human Feedback (RLHF) and understand the key challenges and ethical considerations of enabling real-world LLM applications.

Intermediate Deep Learning with PyTorch

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

Introduction to LLMs in Python

Associate AI Engineer for Data Scientists

Developing Large Language Models

Likely to Recommend

Classifying a restaurant's customer review

“Introduction to LLMs in Python”

Exercise instructions

Hands-on interactive exercise

Introduction to LLMs in Python

Chapter 1: The Large Language Models (LLMs) Landscape

Chapter 2: Building a Transformer Architecture

Chapter 3: Harnessing Pre-trained LLMs

Chapter 4: Evaluating and Leveraging LLMs in the Real World

What is DataCamp?