LFD273 - the course content has been updated (11/4/2024)

fcioanca

Hi,

The course was updated to focus on using the Hugging Face ecosystem for text-related topics and tasks (Transformers, Datasets, Tokenizers). We're now using Datasets as replacements for the discontinued Datapipes, and we're relying on Transformers, Tokenizers, and the Hugging Face Hub to replaced the models and functionalities previously available in the discontinued Torchtext library.

Moving forward, this update brings the course even closer to typical development pipelines used in the industry.

Specifically, the following chapters received significant updates:

• Chapter 5. Building Your First Hugging Face Dataset
• Chapter 8. Pretrained Models for Natural Language Processing
• Chapter 15. Word Embeddings and Text Classification
• Chapter 16. Contextual Word Embeddings with Transformers

To ensure you have access to the latest updates, please clear your cache!

Happy learning!
Flavia
Linux Foundation Education Team