tokenizers/pr_2119/en/api/tokenizer.md

Tokenizer

Tokenizer[[tokenizers.Tokenizer]]

• model (Model) -- The core algorithm that this Tokenizer should be using. A Tokenizer works as a pipeline. It processes some raw text as input and outputs an Encoding.

The pipeline is structured as follows:

1. The Normalizer normalizes the raw input text.
2. The PreTokenizer splits the normalized text into word-level tokens.
3. The Model tokenizes each word into subword tokens and maps them to IDs.
4. The PostProcessor applies any final transformations (e.g., adding special tokens like [CLS] and [SEP]).

Example:

>>> from tokenizers import Tokenizer
>>> from tokenizers.models import BPE
>>> from tokenizers.normalizers import Lowercase
>>> from tokenizers.pre_tokenizers import Whitespace
>>> tokenizer = Tokenizer(BPE(unk_token="<unk>"))
>>> tokenizer.normalizer = Lowercase()
>>> tokenizer.pre_tokenizer = Whitespace()
>>> # Load a pre-built tokenizer from HuggingFace Hub
>>> tokenizer = Tokenizer.from_pretrained("bert-base-uncased")

The optional Decoder in use by the Tokenizer

The Model in use by the Tokenizer

The optional Normalizer in use by the Tokenizer

(dict, optional)A dict with the current padding parameters if padding is enabled Get the current padding parameters

Cannot be set, use enable_padding() instead

The optional PostProcessor in use by the Tokenizer

The optional PreTokenizer in use by the Tokenizer

(dict, optional)A dict with the current truncation parameters if truncation is enabled Get the currently set truncation parameters

Cannot set, use enable_truncation() instead

• tokens (A List of AddedToken or str) -- The list of special tokens we want to add to the vocabulary. Each token can either be a string or an instance of AddedToken for more customization.intThe number of tokens that were created in the vocabulary Add the given special tokens to the Tokenizer.

If these tokens are already part of the vocabulary, it just let the Tokenizer know about them. If they don't exist, the Tokenizer creates them, giving them a new id.

These special tokens will never be processed by the model (ie won't be split into multiple tokens), and they can be removed from the output when decoding.

• tokens (A List of AddedToken or str) -- The list of tokens we want to add to the vocabulary. Each token can be either a string or an instance of AddedToken for more customization.intThe number of tokens that were created in the vocabulary Add the given tokens to the vocabulary

The given tokens are added only if they don't already exist in the vocabulary. Each token then gets a new attributed id.

• sequences (List of List[int]) -- The batch of sequences we want to decode

• skip_special_tokens (bool, defaults to True) -- Whether the special tokens should be removed from the decoded stringsList[str]A list of decoded strings Decode a batch of ids back to their corresponding string

• sequence (~tokenizers.InputSequence) -- The main input sequence we want to encode. This sequence can be either raw text or pre-tokenized, according to the is_pretokenized argument:

  • If is_pretokenized=False: TextInputSequence
  • If is_pretokenized=True: PreTokenizedInputSequence()

• pair (~tokenizers.InputSequence, optional) -- An optional input sequence. The expected format is the same that for sequence.

• is_pretokenized (bool, defaults to False) -- Whether the input is already pre-tokenized

• add_special_tokens (bool, defaults to True) -- Whether to add the special tokensEncodingThe encoded result

Asynchronously encode the given input with character offsets.

This is an async version of encode that can be awaited in async Python code.

Example:

Here are some examples of the inputs that are accepted:

await async_encode("A single sequence")

• input (A List/``Tupleof~tokenizers.EncodeInput) -- A list of single sequences or pair sequences to encode. Each sequence can be either raw text or pre-tokenized, according to the is_pretokenized` argument:

  • If is_pretokenized=False: TextEncodeInput()
  • If is_pretokenized=True: PreTokenizedEncodeInput()

• is_pretokenized (bool, defaults to False) -- Whether the input is already pre-tokenized

• add_special_tokens (bool, defaults to True) -- Whether to add the special tokensA List of [`~tokenizers.Encoding``]The encoded batch

Asynchronously encode the given batch of inputs with character offsets.

This is an async version of encode_batch that can be awaited in async Python code.

Example:

Here are some examples of the inputs that are accepted:

await async_encode_batch([
"A single sequence",
("A tuple with a sequence", "And its pair"),
[ "A", "pre", "tokenized", "sequence" ],
([ "A", "pre", "tokenized", "sequence" ], "And its pair")
])

• input (A List/``Tupleof~tokenizers.EncodeInput) -- A list of single sequences or pair sequences to encode. Each sequence can be either raw text or pre-tokenized, according to the is_pretokenized` argument:

  • If is_pretokenized=False: TextEncodeInput()
  • If is_pretokenized=True: PreTokenizedEncodeInput()

• is_pretokenized (bool, defaults to False) -- Whether the input is already pre-tokenized

• add_special_tokens (bool, defaults to True) -- Whether to add the special tokensA List of [`~tokenizers.Encoding``]The encoded batch

Asynchronously encode the given batch of inputs without tracking character offsets.

This is an async version of encode_batch_fast that can be awaited in async Python code.

Example:

Here are some examples of the inputs that are accepted:

await async_encode_batch_fast([
"A single sequence",
("A tuple with a sequence", "And its pair"),
[ "A", "pre", "tokenized", "sequence" ],
([ "A", "pre", "tokenized", "sequence" ], "And its pair")
])

• ids (A List/Tuple of int) -- The list of ids that we want to decode

• skip_special_tokens (bool, defaults to True) -- Whether the special tokens should be removed from the decoded stringstrThe decoded string Decode the given list of ids back to a string

This is used to decode anything coming back from a Language Model

• sequences (List of List[int]) -- The batch of sequences we want to decode

• skip_special_tokens (bool, defaults to True) -- Whether the special tokens should be removed from the decoded stringsList[str]A list of decoded strings Decode a batch of ids back to their corresponding string

• direction (str, optional, defaults to right) -- The direction in which to pad. Can be either right or left

• pad_to_multiple_of (int, optional) -- If specified, the padding length should always snap to the next multiple of the given value. For example if we were going to pad witha length of 250 but pad_to_multiple_of=8 then we will pad to 256.

• pad_id (int, defaults to 0) -- The id to be used when padding

• pad_type_id (int, defaults to 0) -- The type id to be used when padding

• pad_token (str, defaults to [PAD]) -- The pad token to be used when padding

• length (int, optional) -- If specified, the length at which to pad. If not specified we pad using the size of the longest sequence in a batch. Enable the padding

• max_length (int) -- The max length at which to truncate

• stride (int, optional) -- The length of the previous first sequence to be included in the overflowing sequence

• strategy (str, optional, defaults to longest_first) -- The strategy used to truncation. Can be one of longest_first, only_first or only_second.

• direction (str, defaults to right) -- Truncate direction Enable truncation

• sequence (~tokenizers.InputSequence) -- The main input sequence we want to encode. This sequence can be either raw text or pre-tokenized, according to the is_pretokenized argument:

  • If is_pretokenized=False: TextInputSequence
  • If is_pretokenized=True: PreTokenizedInputSequence()

• pair (~tokenizers.InputSequence, optional) -- An optional input sequence. The expected format is the same that for sequence.

• is_pretokenized (bool, defaults to False) -- Whether the input is already pre-tokenized

• add_special_tokens (bool, defaults to True) -- Whether to add the special tokensEncodingThe encoded result

Encode the given sequence and pair. This method can process raw text sequences as well as already pre-tokenized sequences.

Example:

Here are some examples of the inputs that are accepted:

encode("A single sequence")*
encode("A sequence", "And its pair")*
encode([ "A", "pre", "tokenized", "sequence" ], is_pretokenized=True)`
encode(
[ "A", "pre", "tokenized", "sequence" ], [ "And", "its", "pair" ],
is_pretokenized=True
)

• input (A List/``Tupleof~tokenizers.EncodeInput) -- A list of single sequences or pair sequences to encode. Each sequence can be either raw text or pre-tokenized, according to the is_pretokenized` argument:

  • If is_pretokenized=False: TextEncodeInput()
  • If is_pretokenized=True: PreTokenizedEncodeInput()

• is_pretokenized (bool, defaults to False) -- Whether the input is already pre-tokenized

• add_special_tokens (bool, defaults to True) -- Whether to add the special tokensA List of [`~tokenizers.Encoding``]The encoded batch

Encode the given batch of inputs. This method accept both raw text sequences as well as already pre-tokenized sequences. The reason we use PySequence is because it allows type checking with zero-cost (according to PyO3) as we don't have to convert to check.

Example:

Here are some examples of the inputs that are accepted:

encode_batch([
"A single sequence",
("A tuple with a sequence", "And its pair"),
[ "A", "pre", "tokenized", "sequence" ],
([ "A", "pre", "tokenized", "sequence" ], "And its pair")
])

• input (A List/``Tupleof~tokenizers.EncodeInput) -- A list of single sequences or pair sequences to encode. Each sequence can be either raw text or pre-tokenized, according to the is_pretokenized` argument:

  • If is_pretokenized=False: TextEncodeInput()
  • If is_pretokenized=True: PreTokenizedEncodeInput()

• is_pretokenized (bool, defaults to False) -- Whether the input is already pre-tokenized

• add_special_tokens (bool, defaults to True) -- Whether to add the special tokensA List of [`~tokenizers.Encoding``]The encoded batch

Encode the given batch of inputs. This method is faster than encode_batch because it doesn't keep track of offsets, they will be all zeros.

Example:

Here are some examples of the inputs that are accepted:

encode_batch_fast([
"A single sequence",
("A tuple with a sequence", "And its pair"),
[ "A", "pre", "tokenized", "sequence" ],
([ "A", "pre", "tokenized", "sequence" ], "And its pair")
])

• buffer (bytes) -- A buffer containing a previously serialized TokenizerTokenizerThe new tokenizer Instantiate a new Tokenizer from the given buffer.

• path (str) -- A path to a local JSON file representing a previously serialized TokenizerTokenizerThe new tokenizer Instantiate a new Tokenizer from the file at the given path.

• identifier (str) -- The identifier of a Model on the Hugging Face Hub, that contains a tokenizer.json file

• revision (str, defaults to main) -- A branch or commit id

• token (str, optional, defaults to None) -- An optional auth token used to access private repositories on the Hugging Face HubTokenizerThe new tokenizer Instantiate a new Tokenizer from an existing file on the Hugging Face Hub.

• json (str) -- A valid JSON string representing a previously serialized TokenizerTokenizerThe new tokenizer Instantiate a new Tokenizer from the given JSON string.

Dict[int, AddedToken]The vocabulary Get the underlying vocabulary

• with_added_tokens (bool, defaults to True) -- Whether to include the added tokensDict[str, int]The vocabulary Get the underlying vocabulary

• with_added_tokens (bool, defaults to True) -- Whether to include the added tokensintThe size of the vocabulary Get the size of the underlying vocabulary

• id (int) -- The id to convertOptional[str]An optional token, None if out of vocabulary Convert the given id to its corresponding token if it exists

Disable padding

Disable truncation

Return the number of special tokens that would be added for single/pair sentences. :param is_pair: Boolean indicating if the input would be a single sentence or a pair :return:

• encoding (Encoding) -- The Encoding corresponding to the main sequence.

• pair (Encoding, optional) -- An optional Encoding corresponding to the pair sequence.

• add_special_tokens (bool) -- Whether to add the special tokensEncodingThe final post-processed encoding Apply all the post-processing steps to the given encodings.

The various steps are:

1. Truncate according to the set truncation params (provided with enable_truncation())
2. Apply the PostProcessor
3. Pad according to the set padding params (provided with enable_padding())

• path (str) -- A path to a file in which to save the serialized tokenizer.

• pretty (bool, defaults to True) -- Whether the JSON file should be pretty formatted. Save the Tokenizer to the file at the given path.

• pretty (bool, defaults to False) -- Whether the JSON string should be pretty formatted.strA string representing the serialized Tokenizer Gets a serialized string representing this Tokenizer.

• token (str) -- The token to convertOptional[int]An optional id, None if out of vocabulary Convert the given token to its corresponding id if it exists

• files (List[str]) -- A list of path to the files that we should use for training

• trainer (~tokenizers.trainers.Trainer, optional) -- An optional trainer that should be used to train our Model Train the Tokenizer using the given files.

Reads the files line by line, while keeping all the whitespace, even new lines. If you want to train from data store in-memory, you can check train_from_iterator()

• iterator (Iterator) -- Any iterator over strings or list of strings

• trainer (~tokenizers.trainers.Trainer, optional) -- An optional trainer that should be used to train our Model

• length (int, optional) -- The total number of sequences in the iterator. This is used to provide meaningful progress tracking Train the Tokenizer using the provided iterator.

You can provide anything that is a Python Iterator

• A list of sequences List[str]
• A generator that yields str or List[str]
• A Numpy array of strings
• ...

The Rust API Reference is available directly on the Docs.rs website.

The node API has not been documented yet.