Hugging Face's logo

Buckets:
hf-doc-build
/
doc-dev

Files
xet
hf-doc-build/doc-dev / transformers.js /pr_1472 /en /api /tokenizers.md
rtrm's picture
rtrm
preview code
|
download
raw
110 kB

tokenizers

Tokenizers are used to prepare textual inputs for a model.

Example: Create an AutoTokenizer and use it to tokenize a sentence. This will automatically detect the tokenizer type based on the tokenizer class defined in tokenizer.json.

import { AutoTokenizer } from '@huggingface/transformers';

const tokenizer = await AutoTokenizer.from_pretrained('Xenova/bert-base-uncased');
const { input_ids } = await tokenizer('I love transformers!');
// Tensor {
//   data: BigInt64Array(6) [101n, 1045n, 2293n, 19081n, 999n, 102n],
//   dims: [1, 6],
//   type: 'int64',
//   size: 6,
// }

tokenizers.TokenizerModel ⇐ Callable

Abstract base class for tokenizer models.

Kind: static class of tokenizers
Extends: Callable

new TokenizerModel(config)

Creates a new instance of TokenizerModel.

  ParamTypeDescription




configObjectThe configuration object for the TokenizerModel.

tokenizerModel.vocab : Array.<string>

Kind: instance property of TokenizerModel

tokenizerModel.tokens_to_ids : Map.<string, number>

A mapping of tokens to ids.

Kind: instance property of TokenizerModel

tokenizerModel.fuse_unk : boolean

Whether to fuse unknown tokens when encoding. Defaults to false.

Kind: instance property of TokenizerModel

tokenizerModel._call(tokens) ⇒ Array.<string>

Internal function to call the TokenizerModel instance.

Kind: instance method of TokenizerModel
Overrides: _call
Returns: Array.<string> - The encoded tokens. 

  ParamTypeDescription




tokensArray.&lt;string&gt;The tokens to encode.

tokenizerModel.encode(tokens) ⇒ Array.<string>

Encodes a list of tokens into a list of token IDs.

Kind: instance method of TokenizerModel
Returns: Array.<string> - The encoded tokens.
Throws:

  • Will throw an error if not implemented in a subclass.

    ParamTypeDescription

    tokensArray.<string>The tokens to encode.

tokenizerModel.convert_tokens_to_ids(tokens) ⇒ Array.<number>

Converts a list of tokens into a list of token IDs.

Kind: instance method of TokenizerModel
Returns: Array.<number> - The converted token IDs. 

  ParamTypeDescription




tokensArray.&lt;string&gt;The tokens to convert.

tokenizerModel.convert_ids_to_tokens(ids) ⇒ Array.<string>

Converts a list of token IDs into a list of tokens.

Kind: instance method of TokenizerModel
Returns: Array.<string> - The converted tokens. 

  ParamTypeDescription




idsArray&lt;number&gt; | Array&lt;bigint&gt;The token IDs to convert.

TokenizerModel.fromConfig(config, ...args) ⇒ TokenizerModel

Instantiates a new TokenizerModel instance based on the configuration object provided.

Kind: static method of TokenizerModel
Returns: TokenizerModel - A new instance of a TokenizerModel.
Throws:

  • Will throw an error if the TokenizerModel type in the config is not recognized.

    ParamTypeDescription

    configObjectThe configuration object for the TokenizerModel.

    ...args*Optional arguments to pass to the specific TokenizerModel constructor.

tokenizers.PreTrainedTokenizer

Kind: static class of tokenizers

new PreTrainedTokenizer(tokenizerJSON, tokenizerConfig)

Create a new PreTrainedTokenizer instance.

  ParamTypeDescription




tokenizerJSONObjectThe JSON of the tokenizer.


tokenizerConfigObjectThe config of the tokenizer.

preTrainedTokenizer.added_tokens : Array.<AddedToken>

Kind: instance property of PreTrainedTokenizer

preTrainedTokenizer.added_tokens_map : Map.<string, AddedToken>

Kind: instance property of PreTrainedTokenizer

preTrainedTokenizer.remove_space : boolean

Whether or not to strip the text when tokenizing (removing excess spaces before and after the string).

Kind: instance property of PreTrainedTokenizer

preTrainedTokenizer._call(text, options) ⇒ BatchEncoding

Encode/tokenize the given text(s).

Kind: instance method of PreTrainedTokenizer
Returns: BatchEncoding - Object to be passed to the model. 

  ParamTypeDefaultDescription




textstring | Array&lt;string&gt;The text to tokenize.


optionsObjectAn optional object containing the following properties:


[options.text_pair]string | Array&lt;string&gt;nullOptional second sequence to be encoded. If set, must be the same type as text.


[options.padding]boolean | &#x27;max_length&#x27;falseWhether to pad the input sequences.


[options.add_special_tokens]booleantrueWhether or not to add the special tokens associated with the corresponding model.


[options.truncation]booleanWhether to truncate the input sequences.


[options.max_length]numberMaximum length of the returned list and optionally padding length.


[options.return_tensor]booleantrueWhether to return the results as Tensors or arrays.


[options.return_token_type_ids]booleanWhether to return the token type ids.

preTrainedTokenizer._encode_text(text) ⇒ Array<string> | null

Encodes a single text using the preprocessor pipeline of the tokenizer.

Kind: instance method of PreTrainedTokenizer
Returns: Array<string> | null - The encoded tokens. 

  ParamTypeDescription




textstring | nullThe text to encode.

preTrainedTokenizer._tokenize_helper(text, options) ⇒ *

Internal helper function to tokenize a text, and optionally a pair of texts.

Kind: instance method of PreTrainedTokenizer
Returns: * - An object containing the tokens and optionally the token type IDs. 

  ParamTypeDefaultDescription




textstringThe text to tokenize.


optionsObjectAn optional object containing the following properties:


[options.pair]stringnullThe optional second text to tokenize.


[options.add_special_tokens]booleanfalseWhether or not to add the special tokens associated with the corresponding model.

preTrainedTokenizer.tokenize(text, options) ⇒ Array.<string>

Converts a string into a sequence of tokens.

Kind: instance method of PreTrainedTokenizer
Returns: Array.<string> - The list of tokens. 

  ParamTypeDefaultDescription




textstringThe sequence to be encoded.


optionsObjectAn optional object containing the following properties:


[options.pair]stringA second sequence to be encoded with the first.


[options.add_special_tokens]booleanfalseWhether or not to add the special tokens associated with the corresponding model.

preTrainedTokenizer.encode(text, options) ⇒ Array.<number>

Encodes a single text or a pair of texts using the model's tokenizer.

Kind: instance method of PreTrainedTokenizer
Returns: Array.<number> - An array of token IDs representing the encoded text(s). 

  ParamTypeDefaultDescription




textstringThe text to encode.


optionsObjectAn optional object containing the following properties:


[options.text_pair]stringnullThe optional second text to encode.


[options.add_special_tokens]booleantrueWhether or not to add the special tokens associated with the corresponding model.


[options.return_token_type_ids]booleanWhether to return token_type_ids.

preTrainedTokenizer.batch_decode(batch, decode_args) ⇒ Array.<string>

Decode a batch of tokenized sequences.

Kind: instance method of PreTrainedTokenizer
Returns: Array.<string> - List of decoded sequences. 

  ParamTypeDescription




batchArray&lt;Array&lt;number&gt;&gt; | TensorList/Tensor of tokenized input sequences.


decode_argsObject(Optional) Object with decoding arguments.

preTrainedTokenizer.decode(token_ids, [decode_args]) ⇒ string

Decodes a sequence of token IDs back to a string.

Kind: instance method of PreTrainedTokenizer
Returns: string - The decoded string.
Throws:

  • Error If token_ids is not a non-empty array of integers.

    ParamTypeDefaultDescription

    token_idsArray<number> | Array<bigint> | TensorList/Tensor of token IDs to decode.

    [decode_args]Object{}

    [decode_args.skip_special_tokens]booleanfalseIf true, special tokens are removed from the output string.

    [decode_args.clean_up_tokenization_spaces]booleantrueIf true, spaces before punctuations and abbreviated forms are removed.

preTrainedTokenizer.decode_single(token_ids, decode_args) ⇒ string

Decode a single list of token ids to a string.

Kind: instance method of PreTrainedTokenizer
Returns: string - The decoded string 

  ParamTypeDefaultDescription




token_idsArray&lt;number&gt; | Array&lt;bigint&gt;List of token ids to decode


decode_argsObjectOptional arguments for decoding


[decode_args.skip_special_tokens]booleanfalseWhether to skip special tokens during decoding


[decode_args.clean_up_tokenization_spaces]booleanWhether to clean up tokenization spaces during decoding.

If null, the value is set to this.decoder.cleanup if it exists, falling back to this.clean_up_tokenization_spaces if it exists, falling back to true.

preTrainedTokenizer.get_chat_template(options) ⇒ string

Retrieve the chat template string used for tokenizing chat messages. This template is used internally by the apply_chat_template method and can also be used externally to retrieve the model's chat template for better generation tracking.

Kind: instance method of PreTrainedTokenizer
Returns: string - The chat template string. 

  ParamTypeDefaultDescription




optionsObjectAn optional object containing the following properties:


[options.chat_template]stringnullA Jinja template or the name of a template to use for this conversion.

It is usually not necessary to pass anything to this argument, as the model's template will be used by default.

[options.tools]Array.&lt;Object&gt;A list of tools (callable functions) that will be accessible to the model. If the template does not

support function calling, this argument will have no effect. Each tool should be passed as a JSON Schema, giving the name, description and argument types for the tool. See our chat templating guide for more information.

preTrainedTokenizer.apply_chat_template(conversation, options) ⇒ string | Tensor | Array<number> | Array<Array<number>> | BatchEncoding

Converts a list of message objects with "role" and "content" keys to a list of token ids. This method is intended for use with chat models, and will read the tokenizer's chat_template attribute to determine the format and control tokens to use when converting.

See here for more information.

Example: Applying a chat template to a conversation.

import { AutoTokenizer } from "@huggingface/transformers";

const tokenizer = await AutoTokenizer.from_pretrained("Xenova/mistral-tokenizer-v1");

const chat = [
  { "role": "user", "content": "Hello, how are you?" },
  { "role": "assistant", "content": "I'm doing great. How can I help you today?" },
  { "role": "user", "content": "I'd like to show off how chat templating works!" },
]

const text = tokenizer.apply_chat_template(chat, { tokenize: false });
// "[INST] Hello, how are you? [/INST]I'm doing great. How can I help you today? [INST] I'd like to show off how chat templating works! [/INST]"

const input_ids = tokenizer.apply_chat_template(chat, { tokenize: true, return_tensor: false });
// [1, 733, 16289, 28793, 22557, 28725, 910, 460, 368, 28804, 733, 28748, 16289, 28793, 28737, 28742, 28719, 2548, 1598, 28723, 1602, 541, 315, 1316, 368, 3154, 28804, 2, 28705, 733, 16289, 28793, 315, 28742, 28715, 737, 298, 1347, 805, 910, 10706, 5752, 1077, 3791, 28808, 733, 28748, 16289, 28793]

Kind: instance method of PreTrainedTokenizer
Returns: string | Tensor | Array<number> | Array<Array<number>> | BatchEncoding - The tokenized output. 

  ParamTypeDefaultDescription




conversationArray.&lt;Message&gt;A list of message objects with &quot;role&quot; and &quot;content&quot; keys,

representing the chat history so far.

optionsObjectAn optional object containing the following properties:


[options.chat_template]stringnullA Jinja template to use for this conversion. If

this is not passed, the model's chat template will be used instead.

[options.tools]Array.&lt;Object&gt;A list of tools (callable functions) that will be accessible to the model. If the template does not

support function calling, this argument will have no effect. Each tool should be passed as a JSON Schema, giving the name, description and argument types for the tool. See our chat templating guide for more information.

[options.documents]*A list of dicts representing documents that will be accessible to the model if it is performing RAG

(retrieval-augmented generation). If the template does not support RAG, this argument will have no effect. We recommend that each document should be a dict containing "title" and "text" keys. Please see the RAG section of the chat templating guide for examples of passing documents with chat templates.

[options.add_generation_prompt]booleanfalseWhether to end the prompt with the token(s) that indicate

the start of an assistant message. This is useful when you want to generate a response from the model. Note that this argument will be passed to the chat template, and so it must be supported in the template for this argument to have any effect.

[options.tokenize]booleantrueWhether to tokenize the output. If false, the output will be a string.


[options.padding]booleanfalseWhether to pad sequences to the maximum length. Has no effect if tokenize is false.


[options.truncation]booleanfalseWhether to truncate sequences to the maximum length. Has no effect if tokenize is false.


[options.max_length]numberMaximum length (in tokens) to use for padding or truncation. Has no effect if tokenize is false.

If not specified, the tokenizer's max_length attribute will be used as a default.

[options.return_tensor]booleantrueWhether to return the output as a Tensor or an Array. Has no effect if tokenize is false.


[options.return_dict]booleantrueWhether to return a dictionary with named outputs. Has no effect if tokenize is false.


[options.tokenizer_kwargs]Object{}Additional options to pass to the tokenizer.

PreTrainedTokenizer.from_pretrained(pretrained_model_name_or_path, options) ⇒ Promise.<PreTrainedTokenizer>

Loads a pre-trained tokenizer from the given pretrained_model_name_or_path.

Kind: static method of PreTrainedTokenizer
Returns: Promise.<PreTrainedTokenizer> - A new instance of the PreTrainedTokenizer class.
Throws:

  • Error Throws an error if the tokenizer.json or tokenizer_config.json files are not found in the pretrained_model_name_or_path.

    ParamTypeDescription

    pretrained_model_name_or_pathstringThe path to the pre-trained tokenizer.

    optionsPretrainedTokenizerOptionsAdditional options for loading the tokenizer.

tokenizers.BertTokenizer ⇐ PreTrainedTokenizer

BertTokenizer is a class used to tokenize text for BERT models.

Kind: static class of tokenizers
Extends: PreTrainedTokenizer

tokenizers.AlbertTokenizer ⇐ PreTrainedTokenizer

Albert tokenizer

Kind: static class of tokenizers
Extends: PreTrainedTokenizer

tokenizers.NllbTokenizer

The NllbTokenizer class is used to tokenize text for NLLB ("No Language Left Behind") models.

No Language Left Behind (NLLB) is a first-of-its-kind, AI breakthrough project that open-sources models capable of delivering high-quality translations directly between any pair of 200+ languages — including low-resource languages like Asturian, Luganda, Urdu and more. It aims to help people communicate with anyone, anywhere, regardless of their language preferences. For more information, check out their paper.

For a list of supported languages (along with their language codes),

Kind: static class of tokenizers
See: https://github.com/facebookresearch/flores/blob/main/flores200/README.md#languages-in-flores-200

nllbTokenizer._build_translation_inputs(raw_inputs, tokenizer_options, generate_kwargs) ⇒ Object

Helper function to build translation inputs for an NllbTokenizer.

Kind: instance method of NllbTokenizer
Returns: Object - Object to be passed to the model. 

  ParamTypeDescription




raw_inputsstring | Array&lt;string&gt;The text to tokenize.


tokenizer_optionsObjectOptions to be sent to the tokenizer


generate_kwargsObjectGeneration options.

tokenizers.M2M100Tokenizer

The M2M100Tokenizer class is used to tokenize text for M2M100 ("Many-to-Many") models.

M2M100 is a multilingual encoder-decoder (seq-to-seq) model trained for Many-to-Many multilingual translation. It was introduced in this paper and first released in this repository.

For a list of supported languages (along with their language codes),

Kind: static class of tokenizers
See: https://huggingface.co/facebook/m2m100_418M#languages-covered

m2M100Tokenizer._build_translation_inputs(raw_inputs, tokenizer_options, generate_kwargs) ⇒ Object

Helper function to build translation inputs for an M2M100Tokenizer.

Kind: instance method of M2M100Tokenizer
Returns: Object - Object to be passed to the model. 

  ParamTypeDescription




raw_inputsstring | Array&lt;string&gt;The text to tokenize.


tokenizer_optionsObjectOptions to be sent to the tokenizer


generate_kwargsObjectGeneration options.

tokenizers.WhisperTokenizer ⇐ PreTrainedTokenizer

WhisperTokenizer tokenizer

Kind: static class of tokenizers
Extends: PreTrainedTokenizer

whisperTokenizer._decode_asr(sequences, options) ⇒ *

Decodes automatic speech recognition (ASR) sequences.

Kind: instance method of WhisperTokenizer
Returns: * - The decoded sequences. 

  ParamTypeDescription




sequences*The sequences to decode.


optionsObjectThe options to use for decoding.

whisperTokenizer.decode() : *

Kind: instance method of WhisperTokenizer

tokenizers.MarianTokenizer

Kind: static class of tokenizers
Todo

  • This model is not yet supported by Hugging Face's "fast" tokenizers library (https://github.com/huggingface/tokenizers). Therefore, this implementation (which is based on fast tokenizers) may produce slightly inaccurate results.

new MarianTokenizer(tokenizerJSON, tokenizerConfig)

Create a new MarianTokenizer instance.

  ParamTypeDescription




tokenizerJSONObjectThe JSON of the tokenizer.


tokenizerConfigObjectThe config of the tokenizer.

marianTokenizer._encode_text(text) ⇒ Array

Encodes a single text. Overriding this method is necessary since the language codes must be removed before encoding with sentencepiece model.

Kind: instance method of MarianTokenizer
Returns: Array - The encoded tokens.
See: https://github.com/huggingface/transformers/blob/12d51db243a00726a548a43cc333390ebae731e3/src/transformers/models/marian/tokenization_marian.py#L204-L213 

  ParamTypeDescription




textstring | nullThe text to encode.

tokenizers.AutoTokenizer

Helper class which is used to instantiate pretrained tokenizers with the from_pretrained function. The chosen tokenizer class is determined by the type specified in the tokenizer config.

Kind: static class of tokenizers

new AutoTokenizer()

Example 

const tokenizer = await AutoTokenizer.from_pretrained('Xenova/bert-base-uncased');

AutoTokenizer.from_pretrained(pretrained_model_name_or_path, options) ⇒ Promise.<PreTrainedTokenizer>

Instantiate one of the tokenizer classes of the library from a pretrained model.

The tokenizer class to instantiate is selected based on the tokenizer_class property of the config object (either passed as an argument or loaded from pretrained_model_name_or_path if possible)

Kind: static method of AutoTokenizer
Returns: Promise.<PreTrainedTokenizer> - A new instance of the PreTrainedTokenizer class. 

  ParamTypeDescription




pretrained_model_name_or_pathstringThe name or path of the pretrained model. Can be either:

A string, the model id of a pretrained tokenizer hosted inside a model repo on huggingface.co. Valid model ids can be located at the root-level, like bert-base-uncased, or namespaced under a user or organization name, like dbmdz/bert-base-german-cased. A path to a directory containing tokenizer files, e.g., ./my_model_directory/.

optionsPretrainedTokenizerOptionsAdditional options for loading the tokenizer.

tokenizers.is_chinese_char(cp) ⇒ boolean

Checks whether the given Unicode codepoint represents a CJK (Chinese, Japanese, or Korean) character.

A "chinese character" is defined as anything in the CJK Unicode block: https://en.wikipedia.org/wiki/CJK_Unified_Ideographs_(Unicode_block)

Note that the CJK Unicode block is NOT all Japanese and Korean characters, despite its name. The modern Korean Hangul alphabet is a different block, as is Japanese Hiragana and Katakana. Those alphabets are used to write space-separated words, so they are not treated specially and are handled like all other languages.

Kind: static method of tokenizers
Returns: boolean - True if the codepoint represents a CJK character, false otherwise. 

  ParamTypeDescription




cpnumber | bigintThe Unicode codepoint to check.

tokenizers~AddedToken

Represent a token added by the user on top of the existing Model vocabulary. AddedToken can be configured to specify the behavior they should have in various situations like:

  • Whether they should only match single words
  • Whether to include any whitespace on its left or right

Kind: inner class of tokenizers

new AddedToken(config)

Creates a new instance of AddedToken.

  ParamTypeDefaultDescription




configObjectAdded token configuration object.


config.contentstringThe content of the added token.


config.idnumberThe id of the added token.


[config.single_word]booleanfalseWhether this token must be a single word or can break words.


[config.lstrip]booleanfalseWhether this token should strip whitespaces on its left.


[config.rstrip]booleanfalseWhether this token should strip whitespaces on its right.


[config.normalized]booleanfalseWhether this token should be normalized.


[config.special]booleanfalseWhether this token is special.

tokenizers~WordPieceTokenizer ⇐ TokenizerModel

A subclass of TokenizerModel that uses WordPiece encoding to encode tokens.

Kind: inner class of tokenizers
Extends: TokenizerModel

new WordPieceTokenizer(config) 

  ParamTypeDefaultDescription




configObjectThe configuration object.


config.vocabObjectA mapping of tokens to ids.


config.unk_tokenstringThe unknown token string.


config.continuing_subword_prefixstringThe prefix to use for continuing subwords.


[config.max_input_chars_per_word]number100The maximum number of characters per word.

wordPieceTokenizer.tokens_to_ids : Map.<string, number>

A mapping of tokens to ids.

Kind: instance property of WordPieceTokenizer

wordPieceTokenizer.unk_token_id : number

The id of the unknown token.

Kind: instance property of WordPieceTokenizer

wordPieceTokenizer.unk_token : string

The unknown token string.

Kind: instance property of WordPieceTokenizer

wordPieceTokenizer.max_input_chars_per_word : number

The maximum number of characters allowed per word.

Kind: instance property of WordPieceTokenizer

wordPieceTokenizer.vocab : Array.<string>

An array of tokens.

Kind: instance property of WordPieceTokenizer

wordPieceTokenizer.encode(tokens) ⇒ Array.<string>

Encodes an array of tokens using WordPiece encoding.

Kind: instance method of WordPieceTokenizer
Returns: Array.<string> - An array of encoded tokens. 

  ParamTypeDescription




tokensArray.&lt;string&gt;The tokens to encode.

tokenizers~Unigram ⇐ TokenizerModel

Class representing a Unigram tokenizer model.

Kind: inner class of tokenizers
Extends: TokenizerModel

new Unigram(config, moreConfig)

Create a new Unigram tokenizer model.

  ParamTypeDescription




configObjectThe configuration object for the Unigram model.


config.unk_idnumberThe ID of the unknown token


config.vocab*A 2D array representing a mapping of tokens to scores.


moreConfigObjectAdditional configuration object for the Unigram model.

unigram.scores : Array.<number>

Kind: instance property of Unigram

unigram.populateNodes(lattice)

Populates lattice nodes.

Kind: instance method of Unigram 

  ParamTypeDescription




latticeTokenLatticeThe token lattice to populate with nodes.

unigram.tokenize(normalized) ⇒ Array.<string>

Encodes an array of tokens into an array of subtokens using the unigram model.

Kind: instance method of Unigram
Returns: Array.<string> - An array of subtokens obtained by encoding the input tokens using the unigram model. 

  ParamTypeDescription




normalizedstringThe normalized string.

unigram.encode(tokens) ⇒ Array.<string>

Encodes an array of tokens using Unigram encoding.

Kind: instance method of Unigram
Returns: Array.<string> - An array of encoded tokens. 

  ParamTypeDescription




tokensArray.&lt;string&gt;The tokens to encode.

tokenizers~BPE ⇐ TokenizerModel

BPE class for encoding text into Byte-Pair-Encoding (BPE) tokens.

Kind: inner class of tokenizers
Extends: TokenizerModel

new BPE(config)

Create a BPE instance.

  ParamTypeDefaultDescription




configObjectThe configuration object for BPE.


config.vocabObjectA mapping of tokens to ids.


config.merges*An array of BPE merges as strings.


config.unk_tokenstringThe unknown token used for out of vocabulary words.


config.end_of_word_suffixstringThe suffix to place at the end of each word.


[config.continuing_subword_suffix]stringThe suffix to insert between words.


[config.byte_fallback]booleanfalseWhether to use spm byte-fallback trick (defaults to False)


[config.ignore_merges]booleanfalseWhether or not to match tokens with the vocab before using merges.

bpE.tokens_to_ids : Map.<string, number>

Kind: instance property of BPE

bpE.merges : *

Kind: instance property of BPE

merges.config.merges : *

Kind: static property of merges

bpE.max_length_to_cache

The maximum length we should cache in a model. Strings that are too long have minimal chances to cache hit anyway

Kind: instance property of BPE

bpE.cache_capacity

The default capacity for a BPE's internal cache.

Kind: instance property of BPE

bpE.clear_cache()

Clears the cache.

Kind: instance method of BPE

bpE.bpe(token) ⇒ Array.<string>

Apply Byte-Pair-Encoding (BPE) to a given token. Efficient heap-based priority queue implementation adapted from https://github.com/belladoreai/llama-tokenizer-js.

Kind: instance method of BPE
Returns: Array.<string> - The BPE encoded tokens. 

  ParamTypeDescription




tokenstringThe token to encode.

bpE.encode(tokens) ⇒ Array.<string>

Encodes the input sequence of tokens using the BPE algorithm and returns the resulting subword tokens.

Kind: instance method of BPE
Returns: Array.<string> - The resulting subword tokens after applying the BPE algorithm to the input sequence of tokens. 

  ParamTypeDescription




tokensArray.&lt;string&gt;The input sequence of tokens to encode.

tokenizers~LegacyTokenizerModel

Legacy tokenizer class for tokenizers with only a vocabulary.

Kind: inner class of tokenizers

new LegacyTokenizerModel(config, moreConfig)

Create a LegacyTokenizerModel instance.

  ParamTypeDescription




configObjectThe configuration object for LegacyTokenizerModel.


config.vocabObjectA (possibly nested) mapping of tokens to ids.


moreConfigObjectAdditional configuration object for the LegacyTokenizerModel model.

legacyTokenizerModel.tokens_to_ids : Map.<string, number>

Kind: instance property of LegacyTokenizerModel

tokenizers~Normalizer

A base class for text normalization.

Kind: inner abstract class of tokenizers

new Normalizer(config) 

  ParamTypeDescription




configObjectThe configuration object for the normalizer.

normalizer.normalize(text) ⇒ string

Normalize the input text.

Kind: instance abstract method of Normalizer
Returns: string - The normalized text.
Throws:

  • Error If this method is not implemented in a subclass.

    ParamTypeDescription

    textstringThe text to normalize.

normalizer._call(text) ⇒ string

Alias for Normalizer#normalize.

Kind: instance method of Normalizer
Returns: string - The normalized text. 

  ParamTypeDescription




textstringThe text to normalize.

Normalizer.fromConfig(config) ⇒ Normalizer

Factory method for creating normalizers from config objects.

Kind: static method of Normalizer
Returns: Normalizer - A Normalizer object.
Throws:

  • Error If an unknown Normalizer type is specified in the config.

    ParamTypeDescription

    configObjectThe configuration object for the normalizer.

tokenizers~Replace ⇐ Normalizer

Replace normalizer that replaces occurrences of a pattern with a given string or regular expression.

Kind: inner class of tokenizers
Extends: Normalizer

replace.normalize(text) ⇒ string

Normalize the input text by replacing the pattern with the content.

Kind: instance method of Replace
Returns: string - The normalized text after replacing the pattern with the content. 

  ParamTypeDescription




textstringThe input text to be normalized.

tokenizers~UnicodeNormalizer ⇐ Normalizer

A normalizer that applies Unicode normalization to the input text.

Kind: inner abstract class of tokenizers
Extends: Normalizer

unicodeNormalizer.form : string

The Unicode normalization form to apply.Should be one of: 'NFC', 'NFD', 'NFKC', or 'NFKD'.

Kind: instance property of UnicodeNormalizer

unicodeNormalizer.normalize(text) ⇒ string

Normalize the input text by applying Unicode normalization.

Kind: instance method of UnicodeNormalizer
Returns: string - The normalized text. 

  ParamTypeDescription




textstringThe input text to be normalized.

tokenizers~NFC ⇐ UnicodeNormalizer

A normalizer that applies Unicode normalization form C (NFC) to the input text. Canonical Decomposition, followed by Canonical Composition.

Kind: inner class of tokenizers
Extends: UnicodeNormalizer

tokenizers~NFD ⇐ UnicodeNormalizer

A normalizer that applies Unicode normalization form D (NFD) to the input text. Canonical Decomposition.

Kind: inner class of tokenizers
Extends: UnicodeNormalizer

tokenizers~NFKC ⇐ UnicodeNormalizer

A normalizer that applies Unicode normalization form KC (NFKC) to the input text. Compatibility Decomposition, followed by Canonical Composition.

Kind: inner class of tokenizers
Extends: UnicodeNormalizer

tokenizers~NFKD ⇐ UnicodeNormalizer

A normalizer that applies Unicode normalization form KD (NFKD) to the input text. Compatibility Decomposition.

Kind: inner class of tokenizers
Extends: UnicodeNormalizer

tokenizers~StripNormalizer

A normalizer that strips leading and/or trailing whitespace from the input text.

Kind: inner class of tokenizers

stripNormalizer.normalize(text) ⇒ string

Strip leading and/or trailing whitespace from the input text.

Kind: instance method of StripNormalizer
Returns: string - The normalized text. 

  ParamTypeDescription




textstringThe input text.

tokenizers~StripAccents ⇐ Normalizer

StripAccents normalizer removes all accents from the text.

Kind: inner class of tokenizers
Extends: Normalizer

stripAccents.normalize(text) ⇒ string

Remove all accents from the text.

Kind: instance method of StripAccents
Returns: string - The normalized text without accents. 

  ParamTypeDescription




textstringThe input text.

tokenizers~Lowercase ⇐ Normalizer

A Normalizer that lowercases the input string.

Kind: inner class of tokenizers
Extends: Normalizer

lowercase.normalize(text) ⇒ string

Lowercases the input string.

Kind: instance method of Lowercase
Returns: string - The normalized text. 

  ParamTypeDescription




textstringThe text to normalize.

tokenizers~Prepend ⇐ Normalizer

A Normalizer that prepends a string to the input string.

Kind: inner class of tokenizers
Extends: Normalizer

prepend.normalize(text) ⇒ string

Prepends the input string.

Kind: instance method of Prepend
Returns: string - The normalized text. 

  ParamTypeDescription




textstringThe text to normalize.

tokenizers~NormalizerSequence ⇐ Normalizer

A Normalizer that applies a sequence of Normalizers.

Kind: inner class of tokenizers
Extends: Normalizer

new NormalizerSequence(config)

Create a new instance of NormalizerSequence.

  ParamTypeDescription




configObjectThe configuration object.


config.normalizersArray.&lt;Object&gt;An array of Normalizer configuration objects.

normalizerSequence.normalize(text) ⇒ string

Apply a sequence of Normalizers to the input text.

Kind: instance method of NormalizerSequence
Returns: string - The normalized text. 

  ParamTypeDescription




textstringThe text to normalize.

tokenizers~BertNormalizer ⇐ Normalizer

A class representing a normalizer used in BERT tokenization.

Kind: inner class of tokenizers
Extends: Normalizer

bertNormalizer._tokenize_chinese_chars(text) ⇒ string

Adds whitespace around any CJK (Chinese, Japanese, or Korean) character in the input text.

Kind: instance method of BertNormalizer
Returns: string - The tokenized text with whitespace added around CJK characters. 

  ParamTypeDescription




textstringThe input text to tokenize.

bertNormalizer.stripAccents(text) ⇒ string

Strips accents from the given text.

Kind: instance method of BertNormalizer
Returns: string - The text with accents removed. 

  ParamTypeDescription




textstringThe text to strip accents from.

bertNormalizer.normalize(text) ⇒ string

Normalizes the given text based on the configuration.

Kind: instance method of BertNormalizer
Returns: string - The normalized text. 

  ParamTypeDescription




textstringThe text to normalize.

tokenizers~PreTokenizer ⇐ Callable

A callable class representing a pre-tokenizer used in tokenization. Subclasses should implement the pre_tokenize_text method to define the specific pre-tokenization logic.

Kind: inner class of tokenizers
Extends: Callable

preTokenizer.pre_tokenize_text(text, [options]) ⇒ Array.<string>

Method that should be implemented by subclasses to define the specific pre-tokenization logic.

Kind: instance abstract method of PreTokenizer
Returns: Array.<string> - The pre-tokenized text.
Throws:

  • Error If the method is not implemented in the subclass.

    ParamTypeDescription

    textstringThe text to pre-tokenize.

    [options]ObjectAdditional options for the pre-tokenization logic.

preTokenizer.pre_tokenize(text, [options]) ⇒ Array.<string>

Tokenizes the given text into pre-tokens.

Kind: instance method of PreTokenizer
Returns: Array.<string> - An array of pre-tokens. 

  ParamTypeDescription




textstring | Array&lt;string&gt;The text or array of texts to pre-tokenize.


[options]ObjectAdditional options for the pre-tokenization logic.

preTokenizer._call(text, [options]) ⇒ Array.<string>

Alias for PreTokenizer#pre_tokenize.

Kind: instance method of PreTokenizer
Overrides: _call
Returns: Array.<string> - An array of pre-tokens. 

  ParamTypeDescription




textstring | Array&lt;string&gt;The text or array of texts to pre-tokenize.


[options]ObjectAdditional options for the pre-tokenization logic.

PreTokenizer.fromConfig(config) ⇒ PreTokenizer

Factory method that returns an instance of a subclass of PreTokenizer based on the provided configuration.

Kind: static method of PreTokenizer
Returns: PreTokenizer - An instance of a subclass of PreTokenizer.
Throws:

  • Error If the provided configuration object does not correspond to any known pre-tokenizer.

    ParamTypeDescription

    configObjectA configuration object for the pre-tokenizer.

tokenizers~BertPreTokenizer ⇐ PreTokenizer

Kind: inner class of tokenizers
Extends: PreTokenizer

new BertPreTokenizer(config)

A PreTokenizer that splits text into wordpieces using a basic tokenization scheme similar to that used in the original implementation of BERT.

  ParamTypeDescription




configObjectThe configuration object.

bertPreTokenizer.pre_tokenize_text(text, [options]) ⇒ Array.<string>

Tokenizes a single text using the BERT pre-tokenization scheme.

Kind: instance method of BertPreTokenizer
Returns: Array.<string> - An array of tokens. 

  ParamTypeDescription




textstringThe text to tokenize.


[options]ObjectAdditional options for the pre-tokenization logic.

tokenizers~ByteLevelPreTokenizer ⇐ PreTokenizer

A pre-tokenizer that splits text into Byte-Pair-Encoding (BPE) subwords.

Kind: inner class of tokenizers
Extends: PreTokenizer

new ByteLevelPreTokenizer(config)

Creates a new instance of the ByteLevelPreTokenizer class.

  ParamTypeDescription




configObjectThe configuration object.

byteLevelPreTokenizer.add_prefix_space : boolean

Whether to add a leading space to the first word.This allows to treat the leading word just as any other word.

Kind: instance property of ByteLevelPreTokenizer

byteLevelPreTokenizer.trim_offsets : boolean

Whether the post processing step should trim offsetsto avoid including whitespaces.

Kind: instance property of ByteLevelPreTokenizer
Todo

  • Use this in the pretokenization step.

byteLevelPreTokenizer.use_regex : boolean

Whether to use the standard GPT2 regex for whitespace splitting.Set it to False if you want to use your own splitting. Defaults to true.

Kind: instance property of ByteLevelPreTokenizer

byteLevelPreTokenizer.pre_tokenize_text(text, [options]) ⇒ Array.<string>

Tokenizes a single piece of text using byte-level tokenization.

Kind: instance method of ByteLevelPreTokenizer
Returns: Array.<string> - An array of tokens. 

  ParamTypeDescription




textstringThe text to tokenize.


[options]ObjectAdditional options for the pre-tokenization logic.

tokenizers~SplitPreTokenizer ⇐ PreTokenizer

Splits text using a given pattern.

Kind: inner class of tokenizers
Extends: PreTokenizer

new SplitPreTokenizer(config) 

  ParamTypeDescription




configObjectThe configuration options for the pre-tokenizer.


config.patternObjectThe pattern used to split the text. Can be a string or a regex object.


config.pattern.Stringstring | undefinedThe string to use for splitting. Only defined if the pattern is a string.


config.pattern.Regexstring | undefinedThe regex to use for splitting. Only defined if the pattern is a regex.


config.behaviorSplitDelimiterBehaviorThe behavior to use when splitting.


config.invertbooleanWhether to split (invert=false) or match (invert=true) the pattern.

splitPreTokenizer.pre_tokenize_text(text, [options]) ⇒ Array.<string>

Tokenizes text by splitting it using the given pattern.

Kind: instance method of SplitPreTokenizer
Returns: Array.<string> - An array of tokens. 

  ParamTypeDescription




textstringThe text to tokenize.


[options]ObjectAdditional options for the pre-tokenization logic.

tokenizers~PunctuationPreTokenizer ⇐ PreTokenizer

Splits text based on punctuation.

Kind: inner class of tokenizers
Extends: PreTokenizer

new PunctuationPreTokenizer(config) 

  ParamTypeDescription




configObjectThe configuration options for the pre-tokenizer.


config.behaviorSplitDelimiterBehaviorThe behavior to use when splitting.

punctuationPreTokenizer.pre_tokenize_text(text, [options]) ⇒ Array.<string>

Tokenizes text by splitting it using the given pattern.

Kind: instance method of PunctuationPreTokenizer
Returns: Array.<string> - An array of tokens. 

  ParamTypeDescription




textstringThe text to tokenize.


[options]ObjectAdditional options for the pre-tokenization logic.

tokenizers~DigitsPreTokenizer ⇐ PreTokenizer

Splits text based on digits.

Kind: inner class of tokenizers
Extends: PreTokenizer

new DigitsPreTokenizer(config) 

  ParamTypeDescription




configObjectThe configuration options for the pre-tokenizer.


config.individual_digitsbooleanWhether to split on individual digits.

digitsPreTokenizer.pre_tokenize_text(text, [options]) ⇒ Array.<string>

Tokenizes text by splitting it using the given pattern.

Kind: instance method of DigitsPreTokenizer
Returns: Array.<string> - An array of tokens. 

  ParamTypeDescription




textstringThe text to tokenize.


[options]ObjectAdditional options for the pre-tokenization logic.

tokenizers~PostProcessor ⇐ Callable

Kind: inner class of tokenizers
Extends: Callable

new PostProcessor(config) 

  ParamTypeDescription




configObjectThe configuration for the post-processor.

postProcessor.post_process(tokens, ...args) ⇒ PostProcessedOutput

Method to be implemented in subclass to apply post-processing on the given tokens.

Kind: instance method of PostProcessor
Returns: PostProcessedOutput - The post-processed tokens.
Throws:

  • Error If the method is not implemented in subclass.

    ParamTypeDescription

    tokensArrayThe input tokens to be post-processed.

    ...args*Additional arguments required by the post-processing logic.

postProcessor._call(tokens, ...args) ⇒ PostProcessedOutput

Alias for PostProcessor#post_process.

Kind: instance method of PostProcessor
Overrides: _call
Returns: PostProcessedOutput - The post-processed tokens. 

  ParamTypeDescription




tokensArrayThe text or array of texts to post-process.


...args*Additional arguments required by the post-processing logic.

PostProcessor.fromConfig(config) ⇒ PostProcessor

Factory method to create a PostProcessor object from a configuration object.

Kind: static method of PostProcessor
Returns: PostProcessor - A PostProcessor object created from the given configuration.
Throws:

  • Error If an unknown PostProcessor type is encountered.

    ParamTypeDescription

    configObjectConfiguration object representing a PostProcessor.

tokenizers~BertProcessing

A post-processor that adds special tokens to the beginning and end of the input.

Kind: inner class of tokenizers

new BertProcessing(config) 

  ParamTypeDescription




configObjectThe configuration for the post-processor.


config.clsArray.&lt;string&gt;The special tokens to add to the beginning of the input.


config.sepArray.&lt;string&gt;The special tokens to add to the end of the input.

bertProcessing.post_process(tokens, [tokens_pair]) ⇒ PostProcessedOutput

Adds the special tokens to the beginning and end of the input.

Kind: instance method of BertProcessing
Returns: PostProcessedOutput - The post-processed tokens with the special tokens added to the beginning and end. 

  ParamTypeDefaultDescription




tokensArray.&lt;string&gt;The input tokens.


[tokens_pair]Array.&lt;string&gt;An optional second set of input tokens.

tokenizers~TemplateProcessing ⇐ PostProcessor

Post processor that replaces special tokens in a template with actual tokens.

Kind: inner class of tokenizers
Extends: PostProcessor

new TemplateProcessing(config)

Creates a new instance of TemplateProcessing.

  ParamTypeDescription




configObjectThe configuration options for the post processor.


config.singleArrayThe template for a single sequence of tokens.


config.pairArrayThe template for a pair of sequences of tokens.

templateProcessing.post_process(tokens, [tokens_pair]) ⇒ PostProcessedOutput

Replaces special tokens in the template with actual tokens.

Kind: instance method of TemplateProcessing
Returns: PostProcessedOutput - An object containing the list of tokens with the special tokens replaced with actual tokens. 

  ParamTypeDefaultDescription




tokensArray.&lt;string&gt;The list of tokens for the first sequence.


[tokens_pair]Array.&lt;string&gt;The list of tokens for the second sequence (optional).

tokenizers~ByteLevelPostProcessor ⇐ PostProcessor

A PostProcessor that returns the given tokens as is.

Kind: inner class of tokenizers
Extends: PostProcessor

byteLevelPostProcessor.post_process(tokens, [tokens_pair]) ⇒ PostProcessedOutput

Post process the given tokens.

Kind: instance method of ByteLevelPostProcessor
Returns: PostProcessedOutput - An object containing the post-processed tokens. 

  ParamTypeDefaultDescription




tokensArray.&lt;string&gt;The list of tokens for the first sequence.


[tokens_pair]Array.&lt;string&gt;The list of tokens for the second sequence (optional).

tokenizers~PostProcessorSequence

A post-processor that applies multiple post-processors in sequence.

Kind: inner class of tokenizers

new PostProcessorSequence(config)

Creates a new instance of PostProcessorSequence.

  ParamTypeDescription




configObjectThe configuration object.


config.processorsArray.&lt;Object&gt;The list of post-processors to apply.

postProcessorSequence.post_process(tokens, [tokens_pair]) ⇒ PostProcessedOutput

Post process the given tokens.

Kind: instance method of PostProcessorSequence
Returns: PostProcessedOutput - An object containing the post-processed tokens. 

  ParamTypeDefaultDescription




tokensArray.&lt;string&gt;The list of tokens for the first sequence.


[tokens_pair]Array.&lt;string&gt;The list of tokens for the second sequence (optional).

tokenizers~Decoder ⇐ Callable

The base class for token decoders.

Kind: inner class of tokenizers
Extends: Callable

new Decoder(config)

Creates an instance of Decoder.

  ParamTypeDescription




configObjectThe configuration object.

decoder.added_tokens : Array.<AddedToken>

Kind: instance property of Decoder

decoder._call(tokens) ⇒ string

Calls the decode method.

Kind: instance method of Decoder
Overrides: _call
Returns: string - The decoded string. 

  ParamTypeDescription




tokensArray.&lt;string&gt;The list of tokens.

decoder.decode(tokens) ⇒ string

Decodes a list of tokens.

Kind: instance method of Decoder
Returns: string - The decoded string. 

  ParamTypeDescription




tokensArray.&lt;string&gt;The list of tokens.

decoder.decode_chain(tokens) ⇒ Array.<string>

Apply the decoder to a list of tokens.

Kind: instance method of Decoder
Returns: Array.<string> - The decoded list of tokens.
Throws:

  • Error If the decode_chain method is not implemented in the subclass.

    ParamTypeDescription

    tokensArray.<string>The list of tokens.

Decoder.fromConfig(config) ⇒ Decoder

Creates a decoder instance based on the provided configuration.

Kind: static method of Decoder
Returns: Decoder - A decoder instance.
Throws:

  • Error If an unknown decoder type is provided.

    ParamTypeDescription

    configObjectThe configuration object.

tokenizers~FuseDecoder

Fuse simply fuses all tokens into one big string. It's usually the last decoding step anyway, but this decoder exists incase some decoders need to happen after that step

Kind: inner class of tokenizers

fuseDecoder.decode_chain() : *

Kind: instance method of FuseDecoder

tokenizers~WordPieceDecoder ⇐ Decoder

A decoder that decodes a list of WordPiece tokens into a single string.

Kind: inner class of tokenizers
Extends: Decoder

new WordPieceDecoder(config)

Creates a new instance of WordPieceDecoder.

  ParamTypeDescription




configObjectThe configuration object.


config.prefixstringThe prefix used for WordPiece encoding.


config.cleanupbooleanWhether to cleanup the decoded string.

wordPieceDecoder.decode_chain() : *

Kind: instance method of WordPieceDecoder

tokenizers~ByteLevelDecoder ⇐ Decoder

Byte-level decoder for tokenization output. Inherits from the Decoder class.

Kind: inner class of tokenizers
Extends: Decoder

new ByteLevelDecoder(config)

Create a ByteLevelDecoder object.

  ParamTypeDescription




configObjectConfiguration object.

byteLevelDecoder.convert_tokens_to_string(tokens) ⇒ string

Convert an array of tokens to string by decoding each byte.

Kind: instance method of ByteLevelDecoder
Returns: string - The decoded string. 

  ParamTypeDescription




tokensArray.&lt;string&gt;Array of tokens to be decoded.

byteLevelDecoder.decode_chain() : *

Kind: instance method of ByteLevelDecoder

tokenizers~CTCDecoder

The CTC (Connectionist Temporal Classification) decoder. See https://github.com/huggingface/tokenizers/blob/bb38f390a61883fc2f29d659af696f428d1cda6b/tokenizers/src/decoders/ctc.rs

Kind: inner class of tokenizers

ctcDecoder.convert_tokens_to_string(tokens) ⇒ string

Converts a connectionist-temporal-classification (CTC) output tokens into a single string.

Kind: instance method of CTCDecoder
Returns: string - The decoded string. 

  ParamTypeDescription




tokensArray.&lt;string&gt;Array of tokens to be decoded.

ctcDecoder.decode_chain() : *

Kind: instance method of CTCDecoder

tokenizers~DecoderSequence ⇐ Decoder

Apply a sequence of decoders.

Kind: inner class of tokenizers
Extends: Decoder

new DecoderSequence(config)

Creates a new instance of DecoderSequence.

  ParamTypeDescription




configObjectThe configuration object.


config.decodersArray.&lt;Object&gt;The list of decoders to apply.

decoderSequence.decode_chain() : *

Kind: instance method of DecoderSequence

tokenizers~MetaspacePreTokenizer ⇐ PreTokenizer

This PreTokenizer replaces spaces with the given replacement character, adds a prefix space if requested, and returns a list of tokens.

Kind: inner class of tokenizers
Extends: PreTokenizer

new MetaspacePreTokenizer(config) 

  ParamTypeDefaultDescription




configObjectThe configuration object for the MetaspacePreTokenizer.


config.replacementstringThe character to replace spaces with.


[config.str_rep]string&quot;config.replacement&quot;An optional string representation of the replacement character.


[config.prepend_scheme]&#x27;first&#x27; | &#x27;never&#x27; | &#x27;always&#x27;&#x27;always&#x27;The metaspace prepending scheme.

metaspacePreTokenizer.pre_tokenize_text(text, [options]) ⇒ Array.<string>

This method takes a string, replaces spaces with the replacement character, adds a prefix space if requested, and returns a new list of tokens.

Kind: instance method of MetaspacePreTokenizer
Returns: Array.<string> - A new list of pre-tokenized tokens. 

  ParamTypeDescription




textstringThe text to pre-tokenize.


[options]ObjectThe options for the pre-tokenization.


[options.section_index]numberThe index of the section to pre-tokenize.

tokenizers~MetaspaceDecoder ⇐ Decoder

MetaspaceDecoder class extends the Decoder class and decodes Metaspace tokenization.

Kind: inner class of tokenizers
Extends: Decoder

new MetaspaceDecoder(config)

Constructs a new MetaspaceDecoder object.

  ParamTypeDescription




configObjectThe configuration object for the MetaspaceDecoder.


config.replacementstringThe string to replace spaces with.

metaspaceDecoder.decode_chain() : *

Kind: instance method of MetaspaceDecoder

tokenizers~Precompiled ⇐ Normalizer

A normalizer that applies a precompiled charsmap. This is useful for applying complex normalizations in C++ and exposing them to JavaScript.

Kind: inner class of tokenizers
Extends: Normalizer

new Precompiled(config)

Create a new instance of Precompiled normalizer.

  ParamTypeDescription




configObjectThe configuration object for the Precompiled normalizer.


config.precompiled_charsmapObjectThe precompiled charsmap object.

precompiled.normalize(text) ⇒ string

Normalizes the given text by applying the precompiled charsmap.

Kind: instance method of Precompiled
Returns: string - The normalized text. 

  ParamTypeDescription




textstringThe text to normalize.

tokenizers~PreTokenizerSequence ⇐ PreTokenizer

A pre-tokenizer that applies a sequence of pre-tokenizers to the input text.

Kind: inner class of tokenizers
Extends: PreTokenizer

new PreTokenizerSequence(config)

Creates an instance of PreTokenizerSequence.

  ParamTypeDescription




configObjectThe configuration object for the pre-tokenizer sequence.


config.pretokenizersArray.&lt;Object&gt;An array of pre-tokenizer configurations.

preTokenizerSequence.pre_tokenize_text(text, [options]) ⇒ Array.<string>

Applies each pre-tokenizer in the sequence to the input text in turn.

Kind: instance method of PreTokenizerSequence
Returns: Array.<string> - The pre-tokenized text. 

  ParamTypeDescription




textstringThe text to pre-tokenize.


[options]ObjectAdditional options for the pre-tokenization logic.

tokenizers~WhitespacePreTokenizer

Splits on word boundaries (using the following regular expression: \w+|[^\w\s]+).

Kind: inner class of tokenizers

new WhitespacePreTokenizer(config)

Creates an instance of WhitespacePreTokenizer.

  ParamTypeDescription




configObjectThe configuration object for the pre-tokenizer.

whitespacePreTokenizer.pre_tokenize_text(text, [options]) ⇒ Array.<string>

Pre-tokenizes the input text by splitting it on word boundaries.

Kind: instance method of WhitespacePreTokenizer
Returns: Array.<string> - An array of tokens produced by splitting the input text on whitespace. 

  ParamTypeDescription




textstringThe text to be pre-tokenized.


[options]ObjectAdditional options for the pre-tokenization logic.

tokenizers~WhitespaceSplit ⇐ PreTokenizer

Splits a string of text by whitespace characters into individual tokens.

Kind: inner class of tokenizers
Extends: PreTokenizer

new WhitespaceSplit(config)

Creates an instance of WhitespaceSplit.

  ParamTypeDescription




configObjectThe configuration object for the pre-tokenizer.

whitespaceSplit.pre_tokenize_text(text, [options]) ⇒ Array.<string>

Pre-tokenizes the input text by splitting it on whitespace characters.

Kind: instance method of WhitespaceSplit
Returns: Array.<string> - An array of tokens produced by splitting the input text on whitespace. 

  ParamTypeDescription




textstringThe text to be pre-tokenized.


[options]ObjectAdditional options for the pre-tokenization logic.

tokenizers~ReplacePreTokenizer

Kind: inner class of tokenizers

new ReplacePreTokenizer(config) 

  ParamTypeDescription




configObjectThe configuration options for the pre-tokenizer.


config.patternObjectThe pattern used to split the text. Can be a string or a regex object.


config.contentstringWhat to replace the pattern with.

replacePreTokenizer.pre_tokenize_text(text, [options]) ⇒ Array.<string>

Pre-tokenizes the input text by replacing certain characters.

Kind: instance method of ReplacePreTokenizer
Returns: Array.<string> - An array of tokens produced by replacing certain characters. 

  ParamTypeDescription




textstringThe text to be pre-tokenized.


[options]ObjectAdditional options for the pre-tokenization logic.

tokenizers~FixedLengthPreTokenizer

Kind: inner class of tokenizers

new FixedLengthPreTokenizer(config) 

  ParamTypeDescription




configObjectThe configuration options for the pre-tokenizer.


config.lengthnumberThe fixed length to split the text into.

fixedLengthPreTokenizer.pre_tokenize_text(text, [options]) ⇒ Array.<string>

Pre-tokenizes the input text by splitting it into fixed-length tokens.

Kind: instance method of FixedLengthPreTokenizer
Returns: Array.<string> - An array of tokens produced by splitting the input text into fixed-length tokens. 

  ParamTypeDescription




textstringThe text to be pre-tokenized.


[options]ObjectAdditional options for the pre-tokenization logic.

tokenizers~BYTES_TO_UNICODE ⇒ Object

Returns list of utf-8 byte and a mapping to unicode strings. Specifically avoids mapping to whitespace/control characters the BPE code barfs on.

Kind: inner constant of tokenizers
Returns: Object - Object with utf-8 byte keys and unicode string values.

tokenizers~loadTokenizer(pretrained_model_name_or_path, options) ⇒ Promise.<Array<any>>

Loads a tokenizer from the specified path.

Kind: inner method of tokenizers
Returns: Promise.<Array<any>> - A promise that resolves with information about the loaded tokenizer. 

  ParamTypeDescription




pretrained_model_name_or_pathstringThe path to the tokenizer directory.


optionsPretrainedTokenizerOptionsAdditional options for loading the tokenizer.

tokenizers~regexSplit(text, regex) ⇒ Array.<string>

Helper function to split a string on a regex, but keep the delimiters. This is required, because the JavaScript .split() method does not keep the delimiters, and wrapping in a capturing group causes issues with existing capturing groups (due to nesting).

Kind: inner method of tokenizers
Returns: Array.<string> - The split string. 

  ParamTypeDescription




textstringThe text to split.


regexRegExpThe regex to split on.

tokenizers~createPattern(pattern, invert) ⇒ RegExp | null

Helper method to construct a pattern from a config object.

Kind: inner method of tokenizers
Returns: RegExp | null - The compiled pattern. 

  ParamTypeDefaultDescription




patternObjectThe pattern object.


invertbooleantrueWhether to invert the pattern.

tokenizers~objectToMap(obj) ⇒ Map.<string, any>

Helper function to convert an Object to a Map

Kind: inner method of tokenizers
Returns: Map.<string, any> - The map. 

  ParamTypeDescription




objObjectThe object to convert.

tokenizers~prepareTensorForDecode(tensor) ⇒ Array.<number>

Helper function to convert a tensor to a list before decoding.

Kind: inner method of tokenizers
Returns: Array.<number> - The tensor as a list. 

  ParamTypeDescription




tensorTensorThe tensor to convert.

tokenizers~clean_up_tokenization(text) ⇒ string

Clean up a list of simple English tokenization artifacts like spaces before punctuations and abbreviated forms

Kind: inner method of tokenizers
Returns: string - The cleaned up text. 

  ParamTypeDescription




textstringThe text to clean up.

tokenizers~remove_accents(text) ⇒ string

Helper function to remove accents from a string.

Kind: inner method of tokenizers
Returns: string - The text with accents removed. 

  ParamTypeDescription




textstringThe text to remove accents from.

tokenizers~lowercase_and_remove_accent(text) ⇒ string

Helper function to lowercase a string and remove accents.

Kind: inner method of tokenizers
Returns: string - The lowercased text with accents removed. 

  ParamTypeDescription




textstringThe text to lowercase and remove accents from.

tokenizers~whitespace_split(text) ⇒ Array.<string>

Split a string on whitespace.

Kind: inner method of tokenizers
Returns: Array.<string> - The split string. 

  ParamTypeDescription




textstringThe text to split.

tokenizers~PretrainedTokenizerOptions : Object

Additional tokenizer-specific properties.

Kind: inner typedef of tokenizers
Properties

  NameTypeDefaultDescription




[legacy]booleanfalseWhether or not the legacy behavior of the tokenizer should be used.

tokenizers~BPENode : Object

Kind: inner typedef of tokenizers
Properties

  NameTypeDescription




tokenstringThe token associated with the node


biasnumberA positional bias for the node.


[score]numberThe score of the node.


[prev]BPENodeThe previous node in the linked list.


[next]BPENodeThe next node in the linked list.

tokenizers~SplitDelimiterBehavior : 'removed' | 'isolated' | 'mergedWithPrevious' | 'mergedWithNext' | 'contiguous'

Kind: inner typedef of tokenizers

tokenizers~PostProcessedOutput : Object

Kind: inner typedef of tokenizers
Properties

  NameTypeDescription




tokensArray.&lt;string&gt;List of token produced by the post-processor.


[token_type_ids]Array.&lt;number&gt;List of token type ids produced by the post-processor.

tokenizers~EncodingSingle : Object

Kind: inner typedef of tokenizers
Properties

  NameTypeDescription




input_idsArray.&lt;number&gt;List of token ids to be fed to a model.


attention_maskArray.&lt;number&gt;List of token type ids to be fed to a model


[token_type_ids]Array.&lt;number&gt;List of indices specifying which tokens should be attended to by the model

tokenizers~Message : Object

Kind: inner typedef of tokenizers
Properties

  NameTypeDescription




rolestringThe role of the message (e.g., &quot;user&quot; or &quot;assistant&quot; or &quot;system&quot;).


contentstringThe content of the message.

tokenizers~BatchEncoding : Array<number> | Array<Array<number>> | Tensor

Holds the output of the tokenizer's call function.

Kind: inner typedef of tokenizers
Properties

  NameTypeDescription




input_idsBatchEncodingItemList of token ids to be fed to a model.


attention_maskBatchEncodingItemList of indices specifying which tokens should be attended to by the model.


[token_type_ids]BatchEncodingItemList of token type ids to be fed to a model.

Xet Storage Details

Size:
110 kB
·
Xet hash:
515f52a15b3b748b8168059da11f114dffaaa259ab973692059f209cabea8b44

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.