Hugging Face Fundamentals for Machine Learning
Published by Pearson
Explore the extensive suite of tools for multimodal AI development
- Learn Hugging Face's multimodal AI capabilities, including NLP, image, video, and audio models.
- Gain practical, hands-on experience and build an AI portfolio, relevant for real-world applications.
- Dive into advanced techniques for use in large language models (LLMs).
Learn how to use multimodal AI models on Hugging Face. From navigating the Hugging Face ecosystem with models, datasets, and spaces, to applying advanced techniques in large language models (LLMs), this course covers a wide range of AI capabilities. Join us for a hands-on experience with cutting-edge technologies like the Transformers library for NLP tasks, the Diffusers library for image generation, and innovative video and audio models.
If you’d like to stay ahead in the rapidly evolving field of artificial intelligence, learning platforms like Hugging Face are essential for developers, data scientists, and tech professionals. Whether you're aiming to integrate AI into your projects, lead AI-driven initiatives, or simply stay competitive in the tech landscape, this course offers the tools instruction to allow you to make a significant impact.
What you’ll learn and how you can apply it
- Become comfortable with the Hugging Face platform for developing and deploying AI applications.
- Acquire advanced NLP skills using the Transformers library for tasks like text classification and entity recognition.
- Gain hands-on experience with multimodal AI models for image, video, and audio generation.
- Dive into advanced techniques in large language models (LLMs) to tackle complex AI challenges.
This live event is for you because...
- You're a software developer who wants to enhance your skills with the latest tools and techniques.
- You’re a data scientist aiming to integrate advanced AI solutions into your projects.
- You’re an AI enthusiast with a solid understanding of Python and machine learning, eager to deepen your expertise in cutting-edge AI technologies like NLP, image, and audio models using the Hugging Face platform.
Prerequisites
- Essential Python skills and experience.
- Some experience with Machine Learning is recommended, including model building, training, evaluation, and creating ML/Data pipelines.
- Basic knowledge of NLP and media processing (image, video, audio).
Course Set-up
- Hugging Face account on https://huggingface.co/
- Not essential, but recommended: GPU access on Google Colab on https://colab.research.google.com/
- Course code examples can be found here: https://github.com/nsadawi/HuggingFaceCourse
Recommended Preparation
- Attend: “Hands on NLP with Transformers” by Sinan Ozdemir.
- Watch: AI Catalyst Conference by Jon Krohn
Recommended Follow-up
- Attend “Hugging Face in 4 Hours” by Sinan Ozdemir
- Attend “GenAI Foundations, Fine-Tuning, RAG, and LLM Application Development” by Rob Barton and Jerome Henry
Schedule
The time frames are only estimates and may vary according to how the class is progressing.
Introduction and NLP with Transformers Library on Hugging Face (60 minutes)
- Overview of the Hugging Face platform, its ecosystem, and its significance in AI development.
- Setting up your Hugging Face account, managing tokens, and understanding key resources like models, datasets, and spaces.
- Introduction to the Transformers library and its applications in natural language processing.
- Deep dive into large language models (LLMs) and how they work with a focus on tokenization, their probabilistic nature, text generation, and practical use cases.
- Exercise and Python Code Demo: Implementing NLP pipelines for tasks such as text generation, classification and named entity recognition.
Q&A (10 minutes)
Break (10 minutes)
Image Models and the Diffusers Library with Hugging Face (60 minutes)
- Understanding the role of image models in AI and their integration within the Hugging Face ecosystem.
- Exercise and Python Code Demo: Handling image data in Python, including preprocessing and augmentation techniques.
- Introduction to the Diffusers library and its use in generating high-quality images.
- Practical exercises in setting up and training diffusion models for image generation.
- Exploring advanced techniques and model architectures like U-net within the Diffusers library.
- Exercise and Python Code Demo: Image generation from text using text-to-image models on Hugging Face.
Q&A (10 minutes)
Break (10 minutes)
Audio and Video Models on Hugging Face (60 minutes)
- Overview of audio data and its processing in AI applications.
- Implementing audio models for classification, transcription, and generation tasks.
- Exercise and Python Code Demo: Handling audio data and training models using Hugging Face tools.
- Introduction to video models and their capabilities within Hugging Face.
- Exploring Stable Video Diffusion and I2VGen-XL for creating and enhancing video content
- Exercise and Python Code Demo: Using video generation models from Hugging Face, focusing on transforming static images into videos.
Q&A (10 minutes)
Course wrap-up and next steps (10 minutes)
Your Instructor
Noureddin Sadawi
Dr. Noureddin Sadawi is a consultant in machine/deep learning and data science. He has several years’ experience in various areas involving data manipulation and analysis. He received his PhD from the University of Birmingham, United Kingdom. He is the winner of two international scientific software development contests - at TREC2011 and CLEF2012.
Noureddin is an avid scientific software researcher and developer with a passion for learning and teaching new technologies. He is an experienced scientific software developer and data analyst; over the last few years he has been using Python as his preferred programming language. Also, he has been involved in several projects spanning a variety of fields such as bioinformatics, textual/image/video data analysis, drug discovery, omics data analysis and computer network security. He has taught at multiple universities in the UK and has worked as a software engineer in different roles. He is the founder of SoftLight LTD (https://www.softlight.tech/), a London-based company that specialises in data science and machine/deep learning. Recently, he has joined the University of Oxford as a part-time lecturer.