AI, Data Science & Business Certificates from Google, IBM & Microsoft
Learn Backend Development Part-Time, Online
Overview
Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off
One annual plan covers every course and certificate on Coursera. 40% off for a limited time.
Get Full Access
Explore the various tokenization methods in HuggingFace's transformers library and understand their differences in this informative video. Dive into the process of encoding text into transformer-readable token ID integers, examining five distinct methods and their outputs. Learn about the complexity behind the library's flexibility and ease of use, and gain insights into why multiple tokenization approaches exist. Discover how to build a tokenizer, work with tensors, and perform batch encoding. Access additional resources, including a detailed Medium article and a discounted NLP course, to further enhance your understanding of tokenization in transformers.
Syllabus
Intro
Tokenization
Building a Tokenizer
Tensors
Batch Encode
Tokenizer
Taught by
James Briggs