This part of the course takes a deep dive into the Datasets and Tokenizers libraries, so you’ll learn how to process huge datasets and train your very own tokenizers on them . You’ll also learn about the core NLP tasks that Transformers excel at, and even how to debug your training pipelines effectively.
To celebrate the launch, we’re planning a large community event to which you’re all invited! The event involves two days of talks on Nov 15-16 from experts in the field. To register for the event, please fill out this form : 🤗 Course Community Event
After the talks, you will have the opportunity to collaborate on group projects and demo your work as a Streamlit or Gradio app on Hugging Face Spaces
We’re looking forward to seeing you at the live event and feel free to post any questions you might have here!
Thank you all for creating these courses; I can’t wait to read part II. I read the first part a few months ago, and it helped me complete my bachelor final project and ever since then, I have been learning more and more about your excellent work, transformers, and NLP.