ν ν¬λμ΄μ λ₯Ό μν μ νΈλ¦¬ν° [[utilities-for-tokenizers]]
μ΄ νμ΄μ§λ ν ν¬λμ΄μ μμ μ¬μ©λλ λͺ¨λ μ νΈλ¦¬ν° ν¨μλ€μ λμ΄νλ©°, μ£Όλ‘ [PreTrainedTokenizer]μ [PreTrainedTokenizerFast] μ¬μ΄μ κ³΅ν΅ λ©μλλ₯Ό ꡬννλ [~tokenization_utils_base.PreTrainedTokenizerBase] ν΄λμ€μ [~tokenization_utils_base.SpecialTokensMixin]μ λ€λ£Ήλλ€.
μ΄ ν¨μλ€ λλΆλΆμ λΌμ΄λΈλ¬λ¦¬μ ν ν¬λμ΄μ μ½λλ₯Ό μ°κ΅¬ν λλ§ μ μ©ν©λλ€.
PreTrainedTokenizerBase [[transformers.PreTrainedTokenizerBase]]
[[autodoc]] tokenization_utils_base.PreTrainedTokenizerBase
- call
- all
SpecialTokensMixin [[transformers.SpecialTokensMixin]]
[[autodoc]] tokenization_utils_base.SpecialTokensMixin
Enums λ° namedtuples [[transformers.tokenization_utils_base.TruncationStrategy]]
[[autodoc]] tokenization_utils_base.TruncationStrategy
[[autodoc]] tokenization_utils_base.CharSpan
[[autodoc]] tokenization_utils_base.TokenSpan