Start your journey with the Hugging Face platform by understanding what Hugging Face is and common use cases. Then, you'll learn about the Hugging Face Hub including models and datasets available, how to search for them, navigate model, or dataset, cards, and download. Lastly, you'll learn about the high-level components of transformers and LLMs.

Introduction to Hugging Face

What are Large Language Models?

Use cases for Hugging Face

Transformers and the Hub

Transformer components

Searching the Hub with Python

Saving a model

Working with datasets

Inspecting datasets

Loading datasets

Manipulating datasets

Getting Started with Hugging Face

It's time to dive into the Hugging Face ecosystem! You'll start by learning the basics of the pipeline module and Auto classes from the transformers library. Then, you'll learn at a high level what natural language processing and tokenization is. Finally, you'll start using the pipeline module for several text-based tasks, including text classification.

Pipelines with Hugging Face

Getting started with pipelines

Using AutoClasses

Comparing models with the pipeline

NLP and tokenization

Normalizing text

Comparing tokenizer output

Text classification

Grammatical correctness

Question Natural Language Inference

Zero-shot classification

Summarization

Summarizing long text

Using min_length and max_length

Summarizing several inputs

Building Pipelines with Hugging Face

In this chapter, you'll apply pipeline methodologies to new tasks using image and audio data. Specifically, you will learn ways to process these types of data in preparation for tasks such as classification, question and answering and automatic speech recognition. 

Processing and classifying images

Processing image data

Creating an image classifier

What about the original image?

Question answering and multi-modal tasks

Document question and answering

Visual question and answering

Audio classification

Resampling audio files

Filtering out audio files

Classifying audio files

Automatic speech recognition

Instantiating an ASR pipeline

Word error rate

Iterating over a dataset

Building Pipelines for Image and Audio

Explore the different frameworks for fine-tuning, text generation, and embeddings. Start with the basics of fine-tuning a pre-trained model on a specific dataset and task to improve performance. Then, use Auto classes to generate the text from prompts and images. Finally, you will explore how to generate and use embeddings.

Fine-tuning a model

Preparing a dataset

Building the trainer

Using the fine-tuned model

Text generation

The process of generating text

Generating text from a text prompt

Generating a caption for an image

Embeddings

Use cases for embeddings

Benefits and challenges of embeddings

Generate embeddings for a sentence

Semantic search

Semantic search versus keyword search

Using semantic search

Congratulations

Fine-tuning and Embeddings

english.arrow

imdb_train.arrow

imdb_test.arrow

common_language.arrow

Hugging Face is a vital platform for machine learning and AI tasks due to its robust workflows and extensive model repository. In this course, you'll first explore the basics of Hugging Face, including its components, available models, and datasets. You'll then unlock the potential of state-of-the-art transformers and frameworks for ML and AI tasks, starting with NLP. You'll discover essential pipelines and expand into tasks involving images and audio. The journey concludes with a focus on fine-tuning models and using embeddings for downstream tasks like searching.

In today's rapidly evolving landscape of machine learning (ML) and artificial intelligence (AI), Hugging Face stands out as a vital platform, allowing anyone to leverage the latest advancements in their projects.

<h2>Explore the Hugging Face Hub</h2>

To begin, you'll navigate the Hugging Face Hub's vast model and dataset repository. You'll also discover the power of Large Language Models and Transformers, exploring the diverse range available. You'll discover how the models and datasets can be applied to tasks ranging from sentiment analysis to language translation. Furthermore, we'll extend our exploration to image and audio processing.

<h2>Master Pipelines for Text, Images, and Audio</h2>

Pipelines are the backbone of many ML and AI workflows. You'll start with the basics of the pipeline module and Auto classes from the transformers library. Then, you'll build pipelines for natural language processing tasks before moving on to image and audio processing, ensuring you have the tools to tackle a wide range of tasks efficiently.

<h2>Fine-Tune Models and Leverage Embeddings</h2>

Finally, you'll dive into different frameworks for fine-tuning, text generation, and embeddings. You'll go through a fine-tuning example before exploring the concept of embeddings in machine learning, understanding how they capture semantic information. 

By the end of the course, you'll be equipped with the knowledge and skills to tackle a wide range of ML and AI tasks effectively using the Hugging Face Hub.

Introduction to Functions in Python

Navigate and use the extensive repository of models and datasets available on the Hugging Face Hub.

Zero-shot classification

“Working with Hugging Face”

Exercise instructions

Hands-on interactive exercise

Working with Hugging Face

Chapter 1: Getting Started with Hugging Face

Chapter 2: Building Pipelines with Hugging Face

Chapter 3: Building Pipelines for Image and Audio

Chapter 4: Fine-tuning and Embeddings

What is DataCamp?