Why Are There So Many Tokenization Methods For Transformers?
Five routes to the same destination?
Published in
5 min readJul 27, 2021
HuggingFace’s transformers library is the de-facto standard for NLP — used by practitioners worldwide, it’s powerful, flexible, and easy to use. It achieves this through a fairly large (and complex) code-base, which has resulted in the question:
Why are there so many…