What is a subword-based tokenizer, and what are the strengths and weaknesses of those tokenizers.

This video is part of the Hugging Face course: [ Ссылка ]

Related videos:
- Tokenizers overview: [ Ссылка ]
- Word-based tokenizers: [ Ссылка ]
- Character-based tokenizers: [ Ссылка ]

Have a question? Checkout the forums: [ Ссылка ]
Subscribe to our newsletter: [ Ссылка ]

свернуть