👋 Welcome!
We’ve assembled a toolkit that anyone can use to easily prepare workshops, events, homework or classes. The content is self-contained so that it can be easily incorporated in other material. This content is free and uses well-known Open Source technologies (transformers, gradio, etc).
On June 6 we're organizing a dedicated, free workshop on how to teach these resources in your community. Do not hesitate to register.
Apart from tutorials, we also share other resources to go further into ML or that can assist in designing content.
Would you like to find the tutorials in other languages? You can find all the translations here!
In this tutorial, you get to:
- Explore the over 30,000 models shared in the Hub.
- Learn efficient ways to find the right model and datasets for your own task.
- Learn how to contribute and work collaboratively in your ML workflows
Duration: 20-40 minutes
👉 click here to access the tutorial or 👩🏫 the lecture slides.
In this tutorial, you get to:
- Explore ML demos created by the community.
- Build a quick demo for your machine learning model in Python using the
gradiolibrary- Host the demos for free with Hugging Face Spaces
- Add your demo to the Hugging Face org for your class or conference
Duration: 20-40 minutes
👉 click here to access the tutorial or 👩🏫 the lecture slides.
In this tutorial, you get to:
- Transformer neural networks can be used to tackle a wide range of tasks in natural language processing and beyond.
- Transfer learning allows one to adapt Transformers to specific tasks.
- The
pipeline()function from thetransformerslibrary can be used to run inference with models from the Hugging Face Hub.This tutorial is based on the first of our O'Reilly book Natural Language Processing with Transformers - check it out if you want to dive deeper into the topic!
Duration: 30-45 minutes
In this video, Nate and Lewis give you a guided tour of Transformers and transfer learning, along with an overview of Hugging Face's open science efforts and tools that enable people to work collaboratively in their Machine Learning projects.
We provide a course (free and without ads) that teaches you about natural language processing (NLP) using libraries from the Hugging Face ecosystem.
👉 click here to access the 🤗 Course
💡 This course:- Requires good knowledge of Python
- Is better taken after an introductory deep learning course, such as fast.ai’s Practical Deep Learning for Coders or one of the programs developed by DeepLearning.AI
- Does not expect prior PyTorch or TensorFlow knowledge, though some familiarity with either of those will help
Released February 2022
From experts at Hugging Face, learn all about Transformers and their applications to a wide range of NLP tasks.
👉 click here to visit the book’s website
💡 This book:- Is written for data scientists and machine learning engineers who may have heard about the recent breakthroughs involving transformers, but are lacking an in-depth guide to help them adapt these models to their own use cases.
- Assumes you have some practical experience with training models on GPUs.
- Does not expect prior PyTorch or TensorFlow knowledge, though some familiarity with either of those will help
| Language | Source | Contributors |
|---|---|---|
| Italian | tutorials/IT |
@MorenoLaQuatra |
| Spanish | tutorials/ES |
@Fabioburgos |
| Turkish | tutorials/TR |
@emrecgty @farukozderim |
| French (WIP) | tutorials/FR |
@g0bel1n |
| Hebrew (WIP) | tutorials/HE |
@omer-dor |
| Japanese (WIP) | tutorials/JA |
@Wataru-Nakata |
| Korean (WIP) | tutorials/KO |
@ oikosohn |
| Portuguese (WIP) | tutorials/PT |
@johnnv1 |
| Chinese (WIP) | tutorials/ZH |
@hzwlille |
If you would like to translate the tutorials to your language, see our TRANSLATING guide.
✉️ If you have any questions, please contact violette@huggingface.co!