Buckets:

hf-doc-build
/

doc-dev

Files

xet

hf-doc-build/doc-dev / transformers.js /pr_1452 /en /api /tokenizers.md

rtrm

about 1 month ago

preview code

download

raw

158 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`.
	```javascript
	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](#module_tokenizers)
	* _static_
	* [.TokenizerModel](#module_tokenizers.TokenizerModel) ⇐ [<code>Callable</code>](#Callable)
	* [`new TokenizerModel(config)`](#new_module_tokenizers.TokenizerModel_new)
	* _instance_
	* [`.vocab`](#module_tokenizers.TokenizerModel+vocab) : <code>Array.<string></code>
	* [`.tokens_to_ids`](#module_tokenizers.TokenizerModel+tokens_to_ids) : <code>Map.<string, number></code>
	* [`.fuse_unk`](#module_tokenizers.TokenizerModel+fuse_unk) : <code>boolean</code>
	* [`._call(tokens)`](#module_tokenizers.TokenizerModel+_call) ⇒ <code>Array.<string></code>
	* [`.encode(tokens)`](#module_tokenizers.TokenizerModel+encode) ⇒ <code>Array.<string></code>
	* [`.convert_tokens_to_ids(tokens)`](#module_tokenizers.TokenizerModel+convert_tokens_to_ids) ⇒ <code>Array.<number></code>
	* [`.convert_ids_to_tokens(ids)`](#module_tokenizers.TokenizerModel+convert_ids_to_tokens) ⇒ <code>Array.<string></code>
	* _static_
	* [`.fromConfig(config, ...args)`](#module_tokenizers.TokenizerModel.fromConfig) ⇒ <code>TokenizerModel</code>
	* [.PreTrainedTokenizer](#module_tokenizers.PreTrainedTokenizer)
	* [`new PreTrainedTokenizer(tokenizerJSON, tokenizerConfig)`](#new_module_tokenizers.PreTrainedTokenizer_new)
	* _instance_
	* [`.added_tokens`](#module_tokenizers.PreTrainedTokenizer+added_tokens) : <code>Array.<AddedToken></code>
	* [`.added_tokens_map`](#module_tokenizers.PreTrainedTokenizer+added_tokens_map) : <code>Map.<string, AddedToken></code>
	* [`.remove_space`](#module_tokenizers.PreTrainedTokenizer+remove_space) : <code>boolean</code>
	* [`._call(text, options)`](#module_tokenizers.PreTrainedTokenizer+_call) ⇒ <code>BatchEncoding</code>
	* [`._encode_text(text)`](#module_tokenizers.PreTrainedTokenizer+_encode_text) ⇒ <code>Array<string></code> \| <code>null</code>
	* [`._tokenize_helper(text, options)`](#module_tokenizers.PreTrainedTokenizer+_tokenize_helper) ⇒ <code>*</code>
	* [`.tokenize(text, options)`](#module_tokenizers.PreTrainedTokenizer+tokenize) ⇒ <code>Array.<string></code>
	* [`.encode(text, options)`](#module_tokenizers.PreTrainedTokenizer+encode) ⇒ <code>Array.<number></code>
	* [`.batch_decode(batch, decode_args)`](#module_tokenizers.PreTrainedTokenizer+batch_decode) ⇒ <code>Array.<string></code>
	* [`.decode(token_ids, [decode_args])`](#module_tokenizers.PreTrainedTokenizer+decode) ⇒ <code>string</code>
	* [`.decode_single(token_ids, decode_args)`](#module_tokenizers.PreTrainedTokenizer+decode_single) ⇒ <code>string</code>
	* [`.get_chat_template(options)`](#module_tokenizers.PreTrainedTokenizer+get_chat_template) ⇒ <code>string</code>
	* [`.apply_chat_template(conversation, options)`](#module_tokenizers.PreTrainedTokenizer+apply_chat_template) ⇒ <code>string</code> \| [<code>Tensor</code>](#Tensor) \| <code>Array<number></code> \| <code>Array<Array<number>></code> \| <code>BatchEncoding</code>
	* _static_
	* [`.from_pretrained(pretrained_model_name_or_path, options)`](#module_tokenizers.PreTrainedTokenizer.from_pretrained) ⇒ <code>Promise.<PreTrainedTokenizer></code>
	* [.BertTokenizer](#module_tokenizers.BertTokenizer) ⇐ <code>PreTrainedTokenizer</code>
	* [.AlbertTokenizer](#module_tokenizers.AlbertTokenizer) ⇐ <code>PreTrainedTokenizer</code>
	* [.NllbTokenizer](#module_tokenizers.NllbTokenizer)
	* [`._build_translation_inputs(raw_inputs, tokenizer_options, generate_kwargs)`](#module_tokenizers.NllbTokenizer+_build_translation_inputs) ⇒ <code>Object</code>
	* [.M2M100Tokenizer](#module_tokenizers.M2M100Tokenizer)
	* [`._build_translation_inputs(raw_inputs, tokenizer_options, generate_kwargs)`](#module_tokenizers.M2M100Tokenizer+_build_translation_inputs) ⇒ <code>Object</code>
	* [.WhisperTokenizer](#module_tokenizers.WhisperTokenizer) ⇐ <code>PreTrainedTokenizer</code>
	* [`._decode_asr(sequences, options)`](#module_tokenizers.WhisperTokenizer+_decode_asr) ⇒ <code>*</code>
	* [`.decode()`](#module_tokenizers.WhisperTokenizer+decode) : <code>*</code>
	* [.MarianTokenizer](#module_tokenizers.MarianTokenizer)
	* [`new MarianTokenizer(tokenizerJSON, tokenizerConfig)`](#new_module_tokenizers.MarianTokenizer_new)
	* [`._encode_text(text)`](#module_tokenizers.MarianTokenizer+_encode_text) ⇒ <code>Array</code>
	* [.AutoTokenizer](#module_tokenizers.AutoTokenizer)
	* [`new AutoTokenizer()`](#new_module_tokenizers.AutoTokenizer_new)
	* [`.from_pretrained(pretrained_model_name_or_path, options)`](#module_tokenizers.AutoTokenizer.from_pretrained) ⇒ <code>Promise.<PreTrainedTokenizer></code>
	* [`.is_chinese_char(cp)`](#module_tokenizers.is_chinese_char) ⇒ <code>boolean</code>
	* _inner_
	* [~AddedToken](#module_tokenizers..AddedToken)
	* [`new AddedToken(config)`](#new_module_tokenizers..AddedToken_new)
	* [~WordPieceTokenizer](#module_tokenizers..WordPieceTokenizer) ⇐ <code>TokenizerModel</code>
	* [`new WordPieceTokenizer(config)`](#new_module_tokenizers..WordPieceTokenizer_new)
	* [`.tokens_to_ids`](#module_tokenizers..WordPieceTokenizer+tokens_to_ids) : <code>Map.<string, number></code>
	* [`.unk_token_id`](#module_tokenizers..WordPieceTokenizer+unk_token_id) : <code>number</code>
	* [`.unk_token`](#module_tokenizers..WordPieceTokenizer+unk_token) : <code>string</code>
	* [`.max_input_chars_per_word`](#module_tokenizers..WordPieceTokenizer+max_input_chars_per_word) : <code>number</code>
	* [`.vocab`](#module_tokenizers..WordPieceTokenizer+vocab) : <code>Array.<string></code>
	* [`.encode(tokens)`](#module_tokenizers..WordPieceTokenizer+encode) ⇒ <code>Array.<string></code>
	* [~Unigram](#module_tokenizers..Unigram) ⇐ <code>TokenizerModel</code>
	* [`new Unigram(config, moreConfig)`](#new_module_tokenizers..Unigram_new)
	* [`.scores`](#module_tokenizers..Unigram+scores) : <code>Array.<number></code>
	* [`.populateNodes(lattice)`](#module_tokenizers..Unigram+populateNodes)
	* [`.tokenize(normalized)`](#module_tokenizers..Unigram+tokenize) ⇒ <code>Array.<string></code>
	* [`.encode(tokens)`](#module_tokenizers..Unigram+encode) ⇒ <code>Array.<string></code>
	* [~BPE](#module_tokenizers..BPE) ⇐ <code>TokenizerModel</code>
	* [`new BPE(config)`](#new_module_tokenizers..BPE_new)
	* [`.tokens_to_ids`](#module_tokenizers..BPE+tokens_to_ids) : <code>Map.<string, number></code>
	* [`.merges`](#module_tokenizers..BPE+merges) : <code>*</code>
	* [`.config.merges`](#module_tokenizers..BPE+merges.config.merges) : <code>*</code>
	* [`.max_length_to_cache`](#module_tokenizers..BPE+max_length_to_cache)
	* [`.cache_capacity`](#module_tokenizers..BPE+cache_capacity)
	* [`.clear_cache()`](#module_tokenizers..BPE+clear_cache)
	* [`.bpe(token)`](#module_tokenizers..BPE+bpe) ⇒ <code>Array.<string></code>
	* [`.encode(tokens)`](#module_tokenizers..BPE+encode) ⇒ <code>Array.<string></code>
	* [~LegacyTokenizerModel](#module_tokenizers..LegacyTokenizerModel)
	* [`new LegacyTokenizerModel(config, moreConfig)`](#new_module_tokenizers..LegacyTokenizerModel_new)
	* [`.tokens_to_ids`](#module_tokenizers..LegacyTokenizerModel+tokens_to_ids) : <code>Map.<string, number></code>
	* [~Normalizer](#module_tokenizers..Normalizer)
	* [`new Normalizer(config)`](#new_module_tokenizers..Normalizer_new)
	* _instance_
	* [`.normalize(text)`](#module_tokenizers..Normalizer+normalize) ⇒ <code>string</code>
	* [`._call(text)`](#module_tokenizers..Normalizer+_call) ⇒ <code>string</code>
	* _static_
	* [`.fromConfig(config)`](#module_tokenizers..Normalizer.fromConfig) ⇒ <code>Normalizer</code>
	* [~Replace](#module_tokenizers..Replace) ⇐ <code>Normalizer</code>
	* [`.normalize(text)`](#module_tokenizers..Replace+normalize) ⇒ <code>string</code>
	* [~UnicodeNormalizer](#module_tokenizers..UnicodeNormalizer) ⇐ <code>Normalizer</code>
	* [`.form`](#module_tokenizers..UnicodeNormalizer+form) : <code>string</code>
	* [`.normalize(text)`](#module_tokenizers..UnicodeNormalizer+normalize) ⇒ <code>string</code>
	* [~NFC](#module_tokenizers..NFC) ⇐ <code>UnicodeNormalizer</code>
	* [~NFD](#module_tokenizers..NFD) ⇐ <code>UnicodeNormalizer</code>
	* [~NFKC](#module_tokenizers..NFKC) ⇐ <code>UnicodeNormalizer</code>
	* [~NFKD](#module_tokenizers..NFKD) ⇐ <code>UnicodeNormalizer</code>
	* [~StripNormalizer](#module_tokenizers..StripNormalizer)
	* [`.normalize(text)`](#module_tokenizers..StripNormalizer+normalize) ⇒ <code>string</code>
	* [~StripAccents](#module_tokenizers..StripAccents) ⇐ <code>Normalizer</code>
	* [`.normalize(text)`](#module_tokenizers..StripAccents+normalize) ⇒ <code>string</code>
	* [~Lowercase](#module_tokenizers..Lowercase) ⇐ <code>Normalizer</code>
	* [`.normalize(text)`](#module_tokenizers..Lowercase+normalize) ⇒ <code>string</code>
	* [~Prepend](#module_tokenizers..Prepend) ⇐ <code>Normalizer</code>
	* [`.normalize(text)`](#module_tokenizers..Prepend+normalize) ⇒ <code>string</code>
	* [~NormalizerSequence](#module_tokenizers..NormalizerSequence) ⇐ <code>Normalizer</code>
	* [`new NormalizerSequence(config)`](#new_module_tokenizers..NormalizerSequence_new)
	* [`.normalize(text)`](#module_tokenizers..NormalizerSequence+normalize) ⇒ <code>string</code>
	* [~BertNormalizer](#module_tokenizers..BertNormalizer) ⇐ <code>Normalizer</code>
	* [`._tokenize_chinese_chars(text)`](#module_tokenizers..BertNormalizer+_tokenize_chinese_chars) ⇒ <code>string</code>
	* [`.stripAccents(text)`](#module_tokenizers..BertNormalizer+stripAccents) ⇒ <code>string</code>
	* [`.normalize(text)`](#module_tokenizers..BertNormalizer+normalize) ⇒ <code>string</code>
	* [~PreTokenizer](#module_tokenizers..PreTokenizer) ⇐ [<code>Callable</code>](#Callable)
	* _instance_
	* [`.pre_tokenize_text(text, [options])`](#module_tokenizers..PreTokenizer+pre_tokenize_text) ⇒ <code>Array.<string></code>
	* [`.pre_tokenize(text, [options])`](#module_tokenizers..PreTokenizer+pre_tokenize) ⇒ <code>Array.<string></code>
	* [`._call(text, [options])`](#module_tokenizers..PreTokenizer+_call) ⇒ <code>Array.<string></code>
	* _static_
	* [`.fromConfig(config)`](#module_tokenizers..PreTokenizer.fromConfig) ⇒ <code>PreTokenizer</code>
	* [~BertPreTokenizer](#module_tokenizers..BertPreTokenizer) ⇐ <code>PreTokenizer</code>
	* [`new BertPreTokenizer(config)`](#new_module_tokenizers..BertPreTokenizer_new)
	* [`.pre_tokenize_text(text, [options])`](#module_tokenizers..BertPreTokenizer+pre_tokenize_text) ⇒ <code>Array.<string></code>
	* [~ByteLevelPreTokenizer](#module_tokenizers..ByteLevelPreTokenizer) ⇐ <code>PreTokenizer</code>
	* [`new ByteLevelPreTokenizer(config)`](#new_module_tokenizers..ByteLevelPreTokenizer_new)
	* [`.add_prefix_space`](#module_tokenizers..ByteLevelPreTokenizer+add_prefix_space) : <code>boolean</code>
	* [`.trim_offsets`](#module_tokenizers..ByteLevelPreTokenizer+trim_offsets) : <code>boolean</code>
	* [`.use_regex`](#module_tokenizers..ByteLevelPreTokenizer+use_regex) : <code>boolean</code>
	* [`.pre_tokenize_text(text, [options])`](#module_tokenizers..ByteLevelPreTokenizer+pre_tokenize_text) ⇒ <code>Array.<string></code>
	* [~SplitPreTokenizer](#module_tokenizers..SplitPreTokenizer) ⇐ <code>PreTokenizer</code>
	* [`new SplitPreTokenizer(config)`](#new_module_tokenizers..SplitPreTokenizer_new)
	* [`.pre_tokenize_text(text, [options])`](#module_tokenizers..SplitPreTokenizer+pre_tokenize_text) ⇒ <code>Array.<string></code>
	* [~PunctuationPreTokenizer](#module_tokenizers..PunctuationPreTokenizer) ⇐ <code>PreTokenizer</code>
	* [`new PunctuationPreTokenizer(config)`](#new_module_tokenizers..PunctuationPreTokenizer_new)
	* [`.pre_tokenize_text(text, [options])`](#module_tokenizers..PunctuationPreTokenizer+pre_tokenize_text) ⇒ <code>Array.<string></code>
	* [~DigitsPreTokenizer](#module_tokenizers..DigitsPreTokenizer) ⇐ <code>PreTokenizer</code>
	* [`new DigitsPreTokenizer(config)`](#new_module_tokenizers..DigitsPreTokenizer_new)
	* [`.pre_tokenize_text(text, [options])`](#module_tokenizers..DigitsPreTokenizer+pre_tokenize_text) ⇒ <code>Array.<string></code>
	* [~PostProcessor](#module_tokenizers..PostProcessor) ⇐ [<code>Callable</code>](#Callable)
	* [`new PostProcessor(config)`](#new_module_tokenizers..PostProcessor_new)
	* _instance_
	* [`.post_process(tokens, ...args)`](#module_tokenizers..PostProcessor+post_process) ⇒ <code>PostProcessedOutput</code>
	* [`._call(tokens, ...args)`](#module_tokenizers..PostProcessor+_call) ⇒ <code>PostProcessedOutput</code>
	* _static_
	* [`.fromConfig(config)`](#module_tokenizers..PostProcessor.fromConfig) ⇒ <code>PostProcessor</code>
	* [~BertProcessing](#module_tokenizers..BertProcessing)
	* [`new BertProcessing(config)`](#new_module_tokenizers..BertProcessing_new)
	* [`.post_process(tokens, [tokens_pair])`](#module_tokenizers..BertProcessing+post_process) ⇒ <code>PostProcessedOutput</code>
	* [~TemplateProcessing](#module_tokenizers..TemplateProcessing) ⇐ <code>PostProcessor</code>
	* [`new TemplateProcessing(config)`](#new_module_tokenizers..TemplateProcessing_new)
	* [`.post_process(tokens, [tokens_pair])`](#module_tokenizers..TemplateProcessing+post_process) ⇒ <code>PostProcessedOutput</code>
	* [~ByteLevelPostProcessor](#module_tokenizers..ByteLevelPostProcessor) ⇐ <code>PostProcessor</code>
	* [`.post_process(tokens, [tokens_pair])`](#module_tokenizers..ByteLevelPostProcessor+post_process) ⇒ <code>PostProcessedOutput</code>
	* [~PostProcessorSequence](#module_tokenizers..PostProcessorSequence)
	* [`new PostProcessorSequence(config)`](#new_module_tokenizers..PostProcessorSequence_new)
	* [`.post_process(tokens, [tokens_pair])`](#module_tokenizers..PostProcessorSequence+post_process) ⇒ <code>PostProcessedOutput</code>
	* [~Decoder](#module_tokenizers..Decoder) ⇐ [<code>Callable</code>](#Callable)
	* [`new Decoder(config)`](#new_module_tokenizers..Decoder_new)
	* _instance_
	* [`.added_tokens`](#module_tokenizers..Decoder+added_tokens) : <code>Array.<AddedToken></code>
	* [`._call(tokens)`](#module_tokenizers..Decoder+_call) ⇒ <code>string</code>
	* [`.decode(tokens)`](#module_tokenizers..Decoder+decode) ⇒ <code>string</code>
	* [`.decode_chain(tokens)`](#module_tokenizers..Decoder+decode_chain) ⇒ <code>Array.<string></code>
	* _static_
	* [`.fromConfig(config)`](#module_tokenizers..Decoder.fromConfig) ⇒ <code>Decoder</code>
	* [~FuseDecoder](#module_tokenizers..FuseDecoder)
	* [`.decode_chain()`](#module_tokenizers..FuseDecoder+decode_chain) : <code>*</code>
	* [~WordPieceDecoder](#module_tokenizers..WordPieceDecoder) ⇐ <code>Decoder</code>
	* [`new WordPieceDecoder(config)`](#new_module_tokenizers..WordPieceDecoder_new)
	* [`.decode_chain()`](#module_tokenizers..WordPieceDecoder+decode_chain) : <code>*</code>
	* [~ByteLevelDecoder](#module_tokenizers..ByteLevelDecoder) ⇐ <code>Decoder</code>
	* [`new ByteLevelDecoder(config)`](#new_module_tokenizers..ByteLevelDecoder_new)
	* [`.convert_tokens_to_string(tokens)`](#module_tokenizers..ByteLevelDecoder+convert_tokens_to_string) ⇒ <code>string</code>
	* [`.decode_chain()`](#module_tokenizers..ByteLevelDecoder+decode_chain) : <code>*</code>
	* [~CTCDecoder](#module_tokenizers..CTCDecoder)
	* [`.convert_tokens_to_string(tokens)`](#module_tokenizers..CTCDecoder+convert_tokens_to_string) ⇒ <code>string</code>
	* [`.decode_chain()`](#module_tokenizers..CTCDecoder+decode_chain) : <code>*</code>
	* [~DecoderSequence](#module_tokenizers..DecoderSequence) ⇐ <code>Decoder</code>
	* [`new DecoderSequence(config)`](#new_module_tokenizers..DecoderSequence_new)
	* [`.decode_chain()`](#module_tokenizers..DecoderSequence+decode_chain) : <code>*</code>
	* [~MetaspacePreTokenizer](#module_tokenizers..MetaspacePreTokenizer) ⇐ <code>PreTokenizer</code>
	* [`new MetaspacePreTokenizer(config)`](#new_module_tokenizers..MetaspacePreTokenizer_new)
	* [`.pre_tokenize_text(text, [options])`](#module_tokenizers..MetaspacePreTokenizer+pre_tokenize_text) ⇒ <code>Array.<string></code>
	* [~MetaspaceDecoder](#module_tokenizers..MetaspaceDecoder) ⇐ <code>Decoder</code>
	* [`new MetaspaceDecoder(config)`](#new_module_tokenizers..MetaspaceDecoder_new)
	* [`.decode_chain()`](#module_tokenizers..MetaspaceDecoder+decode_chain) : <code>*</code>
	* [~Precompiled](#module_tokenizers..Precompiled) ⇐ <code>Normalizer</code>
	* [`new Precompiled(config)`](#new_module_tokenizers..Precompiled_new)
	* [`.normalize(text)`](#module_tokenizers..Precompiled+normalize) ⇒ <code>string</code>
	* [~PreTokenizerSequence](#module_tokenizers..PreTokenizerSequence) ⇐ <code>PreTokenizer</code>
	* [`new PreTokenizerSequence(config)`](#new_module_tokenizers..PreTokenizerSequence_new)
	* [`.pre_tokenize_text(text, [options])`](#module_tokenizers..PreTokenizerSequence+pre_tokenize_text) ⇒ <code>Array.<string></code>
	* [~WhitespacePreTokenizer](#module_tokenizers..WhitespacePreTokenizer)
	* [`new WhitespacePreTokenizer(config)`](#new_module_tokenizers..WhitespacePreTokenizer_new)
	* [`.pre_tokenize_text(text, [options])`](#module_tokenizers..WhitespacePreTokenizer+pre_tokenize_text) ⇒ <code>Array.<string></code>
	* [~WhitespaceSplit](#module_tokenizers..WhitespaceSplit) ⇐ <code>PreTokenizer</code>
	* [`new WhitespaceSplit(config)`](#new_module_tokenizers..WhitespaceSplit_new)
	* [`.pre_tokenize_text(text, [options])`](#module_tokenizers..WhitespaceSplit+pre_tokenize_text) ⇒ <code>Array.<string></code>
	* [~ReplacePreTokenizer](#module_tokenizers..ReplacePreTokenizer)
	* [`new ReplacePreTokenizer(config)`](#new_module_tokenizers..ReplacePreTokenizer_new)
	* [`.pre_tokenize_text(text, [options])`](#module_tokenizers..ReplacePreTokenizer+pre_tokenize_text) ⇒ <code>Array.<string></code>
	* [`~BYTES_TO_UNICODE`](#module_tokenizers..BYTES_TO_UNICODE) ⇒ <code>Object</code>
	* [`~loadTokenizer(pretrained_model_name_or_path, options)`](#module_tokenizers..loadTokenizer) ⇒ <code>Promise.<Array<any>></code>
	* [`~regexSplit(text, regex)`](#module_tokenizers..regexSplit) ⇒ <code>Array.<string></code>
	* [`~createPattern(pattern, invert)`](#module_tokenizers..createPattern) ⇒ <code>RegExp</code> \| <code>null</code>
	* [`~objectToMap(obj)`](#module_tokenizers..objectToMap) ⇒ <code>Map.<string, any></code>
	* [`~prepareTensorForDecode(tensor)`](#module_tokenizers..prepareTensorForDecode) ⇒ <code>Array.<number></code>
	* [`~clean_up_tokenization(text)`](#module_tokenizers..clean_up_tokenization) ⇒ <code>string</code>
	* [`~remove_accents(text)`](#module_tokenizers..remove_accents) ⇒ <code>string</code>
	* [`~lowercase_and_remove_accent(text)`](#module_tokenizers..lowercase_and_remove_accent) ⇒ <code>string</code>
	* [`~whitespace_split(text)`](#module_tokenizers..whitespace_split) ⇒ <code>Array.<string></code>
	* [`~PretrainedTokenizerOptions`](#module_tokenizers..PretrainedTokenizerOptions) : <code>Object</code>
	* [`~BPENode`](#module_tokenizers..BPENode) : <code>Object</code>
	* [`~SplitDelimiterBehavior`](#module_tokenizers..SplitDelimiterBehavior) : <code>'removed'</code> \| <code>'isolated'</code> \| <code>'mergedWithPrevious'</code> \| <code>'mergedWithNext'</code> \| <code>'contiguous'</code>
	* [`~PostProcessedOutput`](#module_tokenizers..PostProcessedOutput) : <code>Object</code>
	* [`~EncodingSingle`](#module_tokenizers..EncodingSingle) : <code>Object</code>
	* [`~Message`](#module_tokenizers..Message) : <code>Object</code>
	* [`~BatchEncoding`](#module_tokenizers..BatchEncoding) : <code>Array<number></code> \| <code>Array<Array<number>></code> \| [<code>Tensor</code>](#Tensor)


	* * *

	<a id="module_tokenizers.TokenizerModel" class="group"></a>

	## tokenizers.TokenizerModel ⇐ [<code>Callable</code>](#Callable)

	Abstract base class for tokenizer models.

	Kind: static class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: [<code>Callable</code>](#Callable)

	* [.TokenizerModel](#module_tokenizers.TokenizerModel) ⇐ [<code>Callable</code>](#Callable)
	* [`new TokenizerModel(config)`](#new_module_tokenizers.TokenizerModel_new)
	* _instance_
	* [`.vocab`](#module_tokenizers.TokenizerModel+vocab) : <code>Array.<string></code>
	* [`.tokens_to_ids`](#module_tokenizers.TokenizerModel+tokens_to_ids) : <code>Map.<string, number></code>
	* [`.fuse_unk`](#module_tokenizers.TokenizerModel+fuse_unk) : <code>boolean</code>
	* [`._call(tokens)`](#module_tokenizers.TokenizerModel+_call) ⇒ <code>Array.<string></code>
	* [`.encode(tokens)`](#module_tokenizers.TokenizerModel+encode) ⇒ <code>Array.<string></code>
	* [`.convert_tokens_to_ids(tokens)`](#module_tokenizers.TokenizerModel+convert_tokens_to_ids) ⇒ <code>Array.<number></code>
	* [`.convert_ids_to_tokens(ids)`](#module_tokenizers.TokenizerModel+convert_ids_to_tokens) ⇒ <code>Array.<string></code>
	* _static_
	* [`.fromConfig(config, ...args)`](#module_tokenizers.TokenizerModel.fromConfig) ⇒ <code>TokenizerModel</code>


	* * *

	<a id="new_module_tokenizers.TokenizerModel_new" class="group"></a>

	### `new TokenizerModel(config)`

	Creates a new instance of TokenizerModel.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration object for the TokenizerModel.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers.TokenizerModel+vocab" class="group"></a>

	### `tokenizerModel.vocab` : <code>Array.<string></code>

	Kind: instance property of [<code>TokenizerModel</code>](#module_tokenizers.TokenizerModel)

	* * *

	<a id="module_tokenizers.TokenizerModel+tokens_to_ids" class="group"></a>

	### `tokenizerModel.tokens_to_ids` : <code>Map.<string, number></code>

	A mapping of tokens to ids.

	Kind: instance property of [<code>TokenizerModel</code>](#module_tokenizers.TokenizerModel)

	* * *

	<a id="module_tokenizers.TokenizerModel+fuse_unk" class="group"></a>

	### `tokenizerModel.fuse_unk` : <code>boolean</code>

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

	Kind: instance property of [<code>TokenizerModel</code>](#module_tokenizers.TokenizerModel)

	* * *

	<a id="module_tokenizers.TokenizerModel+_call" class="group"></a>

	### `tokenizerModel._call(tokens)` ⇒ <code>Array.<string></code>

	Internal function to call the TokenizerModel instance.

	Kind: instance method of [<code>TokenizerModel</code>](#module_tokenizers.TokenizerModel)
	Overrides: [<code>_call</code>](#Callable+_call)
	Returns: <code>Array.<string></code> - The encoded tokens.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>tokens</td><td><code>Array.<string></code></td><td><p>The tokens to encode.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers.TokenizerModel+encode" class="group"></a>

	### `tokenizerModel.encode(tokens)` ⇒ <code>Array.<string></code>

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

	Kind: instance method of [<code>TokenizerModel</code>](#module_tokenizers.TokenizerModel)
	Returns: <code>Array.<string></code> - The encoded tokens.
	Throws:

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

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>tokens</td><td><code>Array.<string></code></td><td><p>The tokens to encode.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers.TokenizerModel+convert_tokens_to_ids" class="group"></a>

	### `tokenizerModel.convert_tokens_to_ids(tokens)` ⇒ <code>Array.<number></code>

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

	Kind: instance method of [<code>TokenizerModel</code>](#module_tokenizers.TokenizerModel)
	Returns: <code>Array.<number></code> - The converted token IDs.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>tokens</td><td><code>Array.<string></code></td><td><p>The tokens to convert.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers.TokenizerModel+convert_ids_to_tokens" class="group"></a>

	### `tokenizerModel.convert_ids_to_tokens(ids)` ⇒ <code>Array.<string></code>

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

	Kind: instance method of [<code>TokenizerModel</code>](#module_tokenizers.TokenizerModel)
	Returns: <code>Array.<string></code> - The converted tokens.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>ids</td><td><code>Array<number></code> \| <code>Array<bigint></code></td><td><p>The token IDs to convert.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers.TokenizerModel.fromConfig" class="group"></a>

	### `TokenizerModel.fromConfig(config, ...args)` ⇒ <code>TokenizerModel</code>

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

	Kind: static method of [<code>TokenizerModel</code>](#module_tokenizers.TokenizerModel)
	Returns: <code>TokenizerModel</code> - A new instance of a TokenizerModel.
	Throws:

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

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration object for the TokenizerModel.</p>
	</td>
	</tr><tr>
	<td>...args</td><td><code>*</code></td><td><p>Optional arguments to pass to the specific TokenizerModel constructor.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers.PreTrainedTokenizer" class="group"></a>

	## tokenizers.PreTrainedTokenizer

	Kind: static class of [<code>tokenizers</code>](#module_tokenizers)

	* [.PreTrainedTokenizer](#module_tokenizers.PreTrainedTokenizer)
	* [`new PreTrainedTokenizer(tokenizerJSON, tokenizerConfig)`](#new_module_tokenizers.PreTrainedTokenizer_new)
	* _instance_
	* [`.added_tokens`](#module_tokenizers.PreTrainedTokenizer+added_tokens) : <code>Array.<AddedToken></code>
	* [`.added_tokens_map`](#module_tokenizers.PreTrainedTokenizer+added_tokens_map) : <code>Map.<string, AddedToken></code>
	* [`.remove_space`](#module_tokenizers.PreTrainedTokenizer+remove_space) : <code>boolean</code>
	* [`._call(text, options)`](#module_tokenizers.PreTrainedTokenizer+_call) ⇒ <code>BatchEncoding</code>
	* [`._encode_text(text)`](#module_tokenizers.PreTrainedTokenizer+_encode_text) ⇒ <code>Array<string></code> \| <code>null</code>
	* [`._tokenize_helper(text, options)`](#module_tokenizers.PreTrainedTokenizer+_tokenize_helper) ⇒ <code>*</code>
	* [`.tokenize(text, options)`](#module_tokenizers.PreTrainedTokenizer+tokenize) ⇒ <code>Array.<string></code>
	* [`.encode(text, options)`](#module_tokenizers.PreTrainedTokenizer+encode) ⇒ <code>Array.<number></code>
	* [`.batch_decode(batch, decode_args)`](#module_tokenizers.PreTrainedTokenizer+batch_decode) ⇒ <code>Array.<string></code>
	* [`.decode(token_ids, [decode_args])`](#module_tokenizers.PreTrainedTokenizer+decode) ⇒ <code>string</code>
	* [`.decode_single(token_ids, decode_args)`](#module_tokenizers.PreTrainedTokenizer+decode_single) ⇒ <code>string</code>
	* [`.get_chat_template(options)`](#module_tokenizers.PreTrainedTokenizer+get_chat_template) ⇒ <code>string</code>
	* [`.apply_chat_template(conversation, options)`](#module_tokenizers.PreTrainedTokenizer+apply_chat_template) ⇒ <code>string</code> \| [<code>Tensor</code>](#Tensor) \| <code>Array<number></code> \| <code>Array<Array<number>></code> \| <code>BatchEncoding</code>
	* _static_
	* [`.from_pretrained(pretrained_model_name_or_path, options)`](#module_tokenizers.PreTrainedTokenizer.from_pretrained) ⇒ <code>Promise.<PreTrainedTokenizer></code>


	* * *

	<a id="new_module_tokenizers.PreTrainedTokenizer_new" class="group"></a>

	### `new PreTrainedTokenizer(tokenizerJSON, tokenizerConfig)`

	Create a new PreTrainedTokenizer instance.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>tokenizerJSON</td><td><code>Object</code></td><td><p>The JSON of the tokenizer.</p>
	</td>
	</tr><tr>
	<td>tokenizerConfig</td><td><code>Object</code></td><td><p>The config of the tokenizer.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers.PreTrainedTokenizer+added_tokens" class="group"></a>

	### `preTrainedTokenizer.added_tokens` : <code>Array.<AddedToken></code>

	Kind: instance property of [<code>PreTrainedTokenizer</code>](#module_tokenizers.PreTrainedTokenizer)

	* * *

	<a id="module_tokenizers.PreTrainedTokenizer+added_tokens_map" class="group"></a>

	### `preTrainedTokenizer.added_tokens_map` : <code>Map.<string, AddedToken></code>

	Kind: instance property of [<code>PreTrainedTokenizer</code>](#module_tokenizers.PreTrainedTokenizer)

	* * *

	<a id="module_tokenizers.PreTrainedTokenizer+remove_space" class="group"></a>

	### `preTrainedTokenizer.remove_space` : <code>boolean</code>

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

	Kind: instance property of [<code>PreTrainedTokenizer</code>](#module_tokenizers.PreTrainedTokenizer)

	* * *

	<a id="module_tokenizers.PreTrainedTokenizer+_call" class="group"></a>

	### `preTrainedTokenizer._call(text, options)` ⇒ <code>BatchEncoding</code>

	Encode/tokenize the given text(s).

	Kind: instance method of [<code>PreTrainedTokenizer</code>](#module_tokenizers.PreTrainedTokenizer)
	Returns: <code>BatchEncoding</code> - Object to be passed to the model.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Default</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code> \| <code>Array<string></code></td><td></td><td><p>The text to tokenize.</p>
	</td>
	</tr><tr>
	<td>options</td><td><code>Object</code></td><td></td><td><p>An optional object containing the following properties:</p>
	</td>
	</tr><tr>
	<td>[options.text_pair]</td><td><code>string</code> \| <code>Array<string></code></td><td><code>null</code></td><td><p>Optional second sequence to be encoded. If set, must be the same type as text.</p>
	</td>
	</tr><tr>
	<td>[options.padding]</td><td><code>boolean</code> \| <code>'max_length'</code></td><td><code>false</code></td><td><p>Whether to pad the input sequences.</p>
	</td>
	</tr><tr>
	<td>[options.add_special_tokens]</td><td><code>boolean</code></td><td><code>true</code></td><td><p>Whether or not to add the special tokens associated with the corresponding model.</p>
	</td>
	</tr><tr>
	<td>[options.truncation]</td><td><code>boolean</code></td><td><code></code></td><td><p>Whether to truncate the input sequences.</p>
	</td>
	</tr><tr>
	<td>[options.max_length]</td><td><code>number</code></td><td><code></code></td><td><p>Maximum length of the returned list and optionally padding length.</p>
	</td>
	</tr><tr>
	<td>[options.return_tensor]</td><td><code>boolean</code></td><td><code>true</code></td><td><p>Whether to return the results as Tensors or arrays.</p>
	</td>
	</tr><tr>
	<td>[options.return_token_type_ids]</td><td><code>boolean</code></td><td><code></code></td><td><p>Whether to return the token type ids.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers.PreTrainedTokenizer+_encode_text" class="group"></a>

	### `preTrainedTokenizer._encode_text(text)` ⇒ <code>Array<string></code> \| <code>null</code>

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

	Kind: instance method of [<code>PreTrainedTokenizer</code>](#module_tokenizers.PreTrainedTokenizer)
	Returns: <code>Array<string></code> \| <code>null</code> - The encoded tokens.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code> \| <code>null</code></td><td><p>The text to encode.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers.PreTrainedTokenizer+_tokenize_helper" class="group"></a>

	### `preTrainedTokenizer._tokenize_helper(text, options)` ⇒ <code>*</code>

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

	Kind: instance method of [<code>PreTrainedTokenizer</code>](#module_tokenizers.PreTrainedTokenizer)
	Returns: <code>*</code> - An object containing the tokens and optionally the token type IDs.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Default</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td></td><td><p>The text to tokenize.</p>
	</td>
	</tr><tr>
	<td>options</td><td><code>Object</code></td><td></td><td><p>An optional object containing the following properties:</p>
	</td>
	</tr><tr>
	<td>[options.pair]</td><td><code>string</code></td><td><code>null</code></td><td><p>The optional second text to tokenize.</p>
	</td>
	</tr><tr>
	<td>[options.add_special_tokens]</td><td><code>boolean</code></td><td><code>false</code></td><td><p>Whether or not to add the special tokens associated with the corresponding model.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers.PreTrainedTokenizer+tokenize" class="group"></a>

	### `preTrainedTokenizer.tokenize(text, options)` ⇒ <code>Array.<string></code>

	Converts a string into a sequence of tokens.

	Kind: instance method of [<code>PreTrainedTokenizer</code>](#module_tokenizers.PreTrainedTokenizer)
	Returns: <code>Array.<string></code> - The list of tokens.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Default</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td></td><td><p>The sequence to be encoded.</p>
	</td>
	</tr><tr>
	<td>options</td><td><code>Object</code></td><td></td><td><p>An optional object containing the following properties:</p>
	</td>
	</tr><tr>
	<td>[options.pair]</td><td><code>string</code></td><td></td><td><p>A second sequence to be encoded with the first.</p>
	</td>
	</tr><tr>
	<td>[options.add_special_tokens]</td><td><code>boolean</code></td><td><code>false</code></td><td><p>Whether or not to add the special tokens associated with the corresponding model.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers.PreTrainedTokenizer+encode" class="group"></a>

	### `preTrainedTokenizer.encode(text, options)` ⇒ <code>Array.<number></code>

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

	Kind: instance method of [<code>PreTrainedTokenizer</code>](#module_tokenizers.PreTrainedTokenizer)
	Returns: <code>Array.<number></code> - An array of token IDs representing the encoded text(s).
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Default</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td></td><td><p>The text to encode.</p>
	</td>
	</tr><tr>
	<td>options</td><td><code>Object</code></td><td></td><td><p>An optional object containing the following properties:</p>
	</td>
	</tr><tr>
	<td>[options.text_pair]</td><td><code>string</code></td><td><code>null</code></td><td><p>The optional second text to encode.</p>
	</td>
	</tr><tr>
	<td>[options.add_special_tokens]</td><td><code>boolean</code></td><td><code>true</code></td><td><p>Whether or not to add the special tokens associated with the corresponding model.</p>
	</td>
	</tr><tr>
	<td>[options.return_token_type_ids]</td><td><code>boolean</code></td><td><code></code></td><td><p>Whether to return token_type_ids.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers.PreTrainedTokenizer+batch_decode" class="group"></a>

	### `preTrainedTokenizer.batch_decode(batch, decode_args)` ⇒ <code>Array.<string></code>

	Decode a batch of tokenized sequences.

	Kind: instance method of [<code>PreTrainedTokenizer</code>](#module_tokenizers.PreTrainedTokenizer)
	Returns: <code>Array.<string></code> - List of decoded sequences.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>batch</td><td><code>Array<Array<number>></code> \| <code><a href="#Tensor">Tensor</a></code></td><td><p>List/Tensor of tokenized input sequences.</p>
	</td>
	</tr><tr>
	<td>decode_args</td><td><code>Object</code></td><td><p>(Optional) Object with decoding arguments.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers.PreTrainedTokenizer+decode" class="group"></a>

	### `preTrainedTokenizer.decode(token_ids, [decode_args])` ⇒ <code>string</code>

	Decodes a sequence of token IDs back to a string.

	Kind: instance method of [<code>PreTrainedTokenizer</code>](#module_tokenizers.PreTrainedTokenizer)
	Returns: <code>string</code> - The decoded string.
	Throws:

	- <code>Error</code> If `token_ids` is not a non-empty array of integers.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Default</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>token_ids</td><td><code>Array<number></code> \| <code>Array<bigint></code> \| <code><a href="#Tensor">Tensor</a></code></td><td></td><td><p>List/Tensor of token IDs to decode.</p>
	</td>
	</tr><tr>
	<td>[decode_args]</td><td><code>Object</code></td><td><code>{}</code></td><td></td>
	</tr><tr>
	<td>[decode_args.skip_special_tokens]</td><td><code>boolean</code></td><td><code>false</code></td><td><p>If true, special tokens are removed from the output string.</p>
	</td>
	</tr><tr>
	<td>[decode_args.clean_up_tokenization_spaces]</td><td><code>boolean</code></td><td><code>true</code></td><td><p>If true, spaces before punctuations and abbreviated forms are removed.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers.PreTrainedTokenizer+decode_single" class="group"></a>

	### `preTrainedTokenizer.decode_single(token_ids, decode_args)` ⇒ <code>string</code>

	Decode a single list of token ids to a string.

	Kind: instance method of [<code>PreTrainedTokenizer</code>](#module_tokenizers.PreTrainedTokenizer)
	Returns: <code>string</code> - The decoded string
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Default</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>token_ids</td><td><code>Array<number></code> \| <code>Array<bigint></code></td><td></td><td><p>List of token ids to decode</p>
	</td>
	</tr><tr>
	<td>decode_args</td><td><code>Object</code></td><td></td><td><p>Optional arguments for decoding</p>
	</td>
	</tr><tr>
	<td>[decode_args.skip_special_tokens]</td><td><code>boolean</code></td><td><code>false</code></td><td><p>Whether to skip special tokens during decoding</p>
	</td>
	</tr><tr>
	<td>[decode_args.clean_up_tokenization_spaces]</td><td><code>boolean</code></td><td><code></code></td><td><p>Whether to clean up tokenization spaces during decoding.
	If null, the value is set to <code>this.decoder.cleanup</code> if it exists, falling back to <code>this.clean_up_tokenization_spaces</code> if it exists, falling back to <code>true</code>.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers.PreTrainedTokenizer+get_chat_template" class="group"></a>

	### `preTrainedTokenizer.get_chat_template(options)` ⇒ <code>string</code>

	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 [<code>PreTrainedTokenizer</code>](#module_tokenizers.PreTrainedTokenizer)
	Returns: <code>string</code> - The chat template string.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Default</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>options</td><td><code>Object</code></td><td></td><td><p>An optional object containing the following properties:</p>
	</td>
	</tr><tr>
	<td>[options.chat_template]</td><td><code>string</code></td><td><code>null</code></td><td><p>A 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.</p>
	</td>
	</tr><tr>
	<td>[options.tools]</td><td><code>Array.<Object></code></td><td><code></code></td><td><p>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
	<a href="https://huggingface.co/docs/transformers/main/en/chat_templating#automated-function-conversion-for-tool-use">chat templating guide</a>
	for more information.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers.PreTrainedTokenizer+apply_chat_template" class="group"></a>

	### `preTrainedTokenizer.apply_chat_template(conversation, options)` ⇒ <code>string</code> \| [<code>Tensor</code>](#Tensor) \| <code>Array<number></code> \| <code>Array<Array<number>></code> \| <code>BatchEncoding</code>

	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](https://huggingface.co/docs/transformers/chat_templating) for more information.

	Example: Applying a chat template to a conversation.

	```javascript
	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 });
	// "<s>[INST] Hello, how are you? [/INST]I'm doing great. How can I help you today?</s> [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 [<code>PreTrainedTokenizer</code>](#module_tokenizers.PreTrainedTokenizer)
	Returns: <code>string</code> \| [<code>Tensor</code>](#Tensor) \| <code>Array<number></code> \| <code>Array<Array<number>></code> \| <code>BatchEncoding</code> - The tokenized output.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Default</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>conversation</td><td><code>Array.<Message></code></td><td></td><td><p>A list of message objects with <code>"role"</code> and <code>"content"</code> keys,
	representing the chat history so far.</p>
	</td>
	</tr><tr>
	<td>options</td><td><code>Object</code></td><td></td><td><p>An optional object containing the following properties:</p>
	</td>
	</tr><tr>
	<td>[options.chat_template]</td><td><code>string</code></td><td><code>null</code></td><td><p>A Jinja template to use for this conversion. If
	this is not passed, the model's chat template will be used instead.</p>
	</td>
	</tr><tr>
	<td>[options.tools]</td><td><code>Array.<Object></code></td><td><code></code></td><td><p>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
	<a href="https://huggingface.co/docs/transformers/main/en/chat_templating#automated-function-conversion-for-tool-use">chat templating guide</a>
	for more information.</p>
	</td>
	</tr><tr>
	<td>[options.documents]</td><td><code>*</code></td><td><code></code></td><td><p>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 <a href="https://huggingface.co/docs/transformers/main/en/chat_templating#arguments-for-RAG">chat templating guide</a>
	for examples of passing documents with chat templates.</p>
	</td>
	</tr><tr>
	<td>[options.add_generation_prompt]</td><td><code>boolean</code></td><td><code>false</code></td><td><p>Whether 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.</p>
	</td>
	</tr><tr>
	<td>[options.tokenize]</td><td><code>boolean</code></td><td><code>true</code></td><td><p>Whether to tokenize the output. If false, the output will be a string.</p>
	</td>
	</tr><tr>
	<td>[options.padding]</td><td><code>boolean</code></td><td><code>false</code></td><td><p>Whether to pad sequences to the maximum length. Has no effect if tokenize is false.</p>
	</td>
	</tr><tr>
	<td>[options.truncation]</td><td><code>boolean</code></td><td><code>false</code></td><td><p>Whether to truncate sequences to the maximum length. Has no effect if tokenize is false.</p>
	</td>
	</tr><tr>
	<td>[options.max_length]</td><td><code>number</code></td><td><code></code></td><td><p>Maximum length (in tokens) to use for padding or truncation. Has no effect if tokenize is false.
	If not specified, the tokenizer's <code>max_length</code> attribute will be used as a default.</p>
	</td>
	</tr><tr>
	<td>[options.return_tensor]</td><td><code>boolean</code></td><td><code>true</code></td><td><p>Whether to return the output as a Tensor or an Array. Has no effect if tokenize is false.</p>
	</td>
	</tr><tr>
	<td>[options.return_dict]</td><td><code>boolean</code></td><td><code>true</code></td><td><p>Whether to return a dictionary with named outputs. Has no effect if tokenize is false.</p>
	</td>
	</tr><tr>
	<td>[options.tokenizer_kwargs]</td><td><code>Object</code></td><td><code>{}</code></td><td><p>Additional options to pass to the tokenizer.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers.PreTrainedTokenizer.from_pretrained" class="group"></a>

	### `PreTrainedTokenizer.from_pretrained(pretrained_model_name_or_path, options)` ⇒ <code>Promise.<PreTrainedTokenizer></code>

	Loads a pre-trained tokenizer from the given `pretrained_model_name_or_path`.

	Kind: static method of [<code>PreTrainedTokenizer</code>](#module_tokenizers.PreTrainedTokenizer)
	Returns: <code>Promise.<PreTrainedTokenizer></code> - A new instance of the `PreTrainedTokenizer` class.
	Throws:

	- <code>Error</code> Throws an error if the tokenizer.json or tokenizer_config.json files are not found in the `pretrained_model_name_or_path`.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>pretrained_model_name_or_path</td><td><code>string</code></td><td><p>The path to the pre-trained tokenizer.</p>
	</td>
	</tr><tr>
	<td>options</td><td><code>PretrainedTokenizerOptions</code></td><td><p>Additional options for loading the tokenizer.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers.BertTokenizer" class="group"></a>

	## tokenizers.BertTokenizer ⇐ <code>PreTrainedTokenizer</code>

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

	Kind: static class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>PreTrainedTokenizer</code>

	* * *

	<a id="module_tokenizers.AlbertTokenizer" class="group"></a>

	## tokenizers.AlbertTokenizer ⇐ <code>PreTrainedTokenizer</code>

	Albert tokenizer

	Kind: static class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>PreTrainedTokenizer</code>

	* * *

	<a id="module_tokenizers.NllbTokenizer" class="group"></a>

	## 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](https://huggingface.co/papers/2207.04672).

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

	Kind: static class of [<code>tokenizers</code>](#module_tokenizers)
	See: [https://github.com/facebookresearch/flores/blob/main/flores200/README.md#languages-in-flores-200](https://github.com/facebookresearch/flores/blob/main/flores200/README.md#languages-in-flores-200)

	* * *

	<a id="module_tokenizers.NllbTokenizer+_build_translation_inputs" class="group"></a>

	### `nllbTokenizer._build_translation_inputs(raw_inputs, tokenizer_options, generate_kwargs)` ⇒ <code>Object</code>

	Helper function to build translation inputs for an `NllbTokenizer`.

	Kind: instance method of [<code>NllbTokenizer</code>](#module_tokenizers.NllbTokenizer)
	Returns: <code>Object</code> - Object to be passed to the model.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>raw_inputs</td><td><code>string</code> \| <code>Array<string></code></td><td><p>The text to tokenize.</p>
	</td>
	</tr><tr>
	<td>tokenizer_options</td><td><code>Object</code></td><td><p>Options to be sent to the tokenizer</p>
	</td>
	</tr><tr>
	<td>generate_kwargs</td><td><code>Object</code></td><td><p>Generation options.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers.M2M100Tokenizer" class="group"></a>

	## 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](https://huggingface.co/papers/2010.11125)
	and first released in [this](https://github.com/pytorch/fairseq/tree/master/examples/m2m_100) repository.

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

	Kind: static class of [<code>tokenizers</code>](#module_tokenizers)
	See: [https://huggingface.co/facebook/m2m100_418M#languages-covered](https://huggingface.co/facebook/m2m100_418M#languages-covered)

	* * *

	<a id="module_tokenizers.M2M100Tokenizer+_build_translation_inputs" class="group"></a>

	### `m2M100Tokenizer._build_translation_inputs(raw_inputs, tokenizer_options, generate_kwargs)` ⇒ <code>Object</code>

	Helper function to build translation inputs for an `M2M100Tokenizer`.

	Kind: instance method of [<code>M2M100Tokenizer</code>](#module_tokenizers.M2M100Tokenizer)
	Returns: <code>Object</code> - Object to be passed to the model.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>raw_inputs</td><td><code>string</code> \| <code>Array<string></code></td><td><p>The text to tokenize.</p>
	</td>
	</tr><tr>
	<td>tokenizer_options</td><td><code>Object</code></td><td><p>Options to be sent to the tokenizer</p>
	</td>
	</tr><tr>
	<td>generate_kwargs</td><td><code>Object</code></td><td><p>Generation options.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers.WhisperTokenizer" class="group"></a>

	## tokenizers.WhisperTokenizer ⇐ <code>PreTrainedTokenizer</code>

	WhisperTokenizer tokenizer

	Kind: static class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>PreTrainedTokenizer</code>

	* [.WhisperTokenizer](#module_tokenizers.WhisperTokenizer) ⇐ <code>PreTrainedTokenizer</code>
	* [`._decode_asr(sequences, options)`](#module_tokenizers.WhisperTokenizer+_decode_asr) ⇒ <code>*</code>
	* [`.decode()`](#module_tokenizers.WhisperTokenizer+decode) : <code>*</code>


	* * *

	<a id="module_tokenizers.WhisperTokenizer+_decode_asr" class="group"></a>

	### `whisperTokenizer._decode_asr(sequences, options)` ⇒ <code>*</code>

	Decodes automatic speech recognition (ASR) sequences.

	Kind: instance method of [<code>WhisperTokenizer</code>](#module_tokenizers.WhisperTokenizer)
	Returns: <code>*</code> - The decoded sequences.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>sequences</td><td><code>*</code></td><td><p>The sequences to decode.</p>
	</td>
	</tr><tr>
	<td>options</td><td><code>Object</code></td><td><p>The options to use for decoding.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers.WhisperTokenizer+decode" class="group"></a>

	### `whisperTokenizer.decode()` : <code>*</code>

	Kind: instance method of [<code>WhisperTokenizer</code>](#module_tokenizers.WhisperTokenizer)

	* * *

	<a id="module_tokenizers.MarianTokenizer" class="group"></a>

	## tokenizers.MarianTokenizer

	Kind: static class of [<code>tokenizers</code>](#module_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.


	* [.MarianTokenizer](#module_tokenizers.MarianTokenizer)
	* [`new MarianTokenizer(tokenizerJSON, tokenizerConfig)`](#new_module_tokenizers.MarianTokenizer_new)
	* [`._encode_text(text)`](#module_tokenizers.MarianTokenizer+_encode_text) ⇒ <code>Array</code>


	* * *

	<a id="new_module_tokenizers.MarianTokenizer_new" class="group"></a>

	### `new MarianTokenizer(tokenizerJSON, tokenizerConfig)`

	Create a new MarianTokenizer instance.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>tokenizerJSON</td><td><code>Object</code></td><td><p>The JSON of the tokenizer.</p>
	</td>
	</tr><tr>
	<td>tokenizerConfig</td><td><code>Object</code></td><td><p>The config of the tokenizer.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers.MarianTokenizer+_encode_text" class="group"></a>

	### `marianTokenizer._encode_text(text)` ⇒ <code>Array</code>

	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 [<code>MarianTokenizer</code>](#module_tokenizers.MarianTokenizer)
	Returns: <code>Array</code> - The encoded tokens.
	See: https://github.com/huggingface/transformers/blob/12d51db243a00726a548a43cc333390ebae731e3/src/transformers/models/marian/tokenization_marian.py#L204-L213
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code> \| <code>null</code></td><td><p>The text to encode.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers.AutoTokenizer" class="group"></a>

	## 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 [<code>tokenizers</code>](#module_tokenizers)

	* [.AutoTokenizer](#module_tokenizers.AutoTokenizer)
	* [`new AutoTokenizer()`](#new_module_tokenizers.AutoTokenizer_new)
	* [`.from_pretrained(pretrained_model_name_or_path, options)`](#module_tokenizers.AutoTokenizer.from_pretrained) ⇒ <code>Promise.<PreTrainedTokenizer></code>


	* * *

	<a id="new_module_tokenizers.AutoTokenizer_new" class="group"></a>

	### `new AutoTokenizer()`

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

	* * *

	<a id="module_tokenizers.AutoTokenizer.from_pretrained" class="group"></a>

	### `AutoTokenizer.from_pretrained(pretrained_model_name_or_path, options)` ⇒ <code>Promise.<PreTrainedTokenizer></code>

	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 [<code>AutoTokenizer</code>](#module_tokenizers.AutoTokenizer)
	Returns: <code>Promise.<PreTrainedTokenizer></code> - A new instance of the PreTrainedTokenizer class.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>pretrained_model_name_or_path</td><td><code>string</code></td><td><p>The name or path of the pretrained model. Can be either:</p>
	<ul>
	<li>A string, the <em>model id</em> of a pretrained tokenizer hosted inside a model repo on huggingface.co.
	Valid model ids can be located at the root-level, like <code>bert-base-uncased</code>, or namespaced under a
	user or organization name, like <code>dbmdz/bert-base-german-cased</code>.</li>
	<li>A path to a <em>directory</em> containing tokenizer files, e.g., <code>./my_model_directory/</code>.</li>
	</ul>
	</td>
	</tr><tr>
	<td>options</td><td><code>PretrainedTokenizerOptions</code></td><td><p>Additional options for loading the tokenizer.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers.is_chinese_char" class="group"></a>

	## `tokenizers.is_chinese_char(cp)` ⇒ <code>boolean</code>

	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 [<code>tokenizers</code>](#module_tokenizers)
	Returns: <code>boolean</code> - True if the codepoint represents a CJK character, false otherwise.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>cp</td><td><code>number</code> \| <code>bigint</code></td><td><p>The Unicode codepoint to check.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..AddedToken" class="group"></a>

	## 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 [<code>tokenizers</code>](#module_tokenizers)

	* * *

	<a id="new_module_tokenizers..AddedToken_new" class="group"></a>

	### `new AddedToken(config)`

	Creates a new instance of AddedToken.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Default</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td></td><td><p>Added token configuration object.</p>
	</td>
	</tr><tr>
	<td>config.content</td><td><code>string</code></td><td></td><td><p>The content of the added token.</p>
	</td>
	</tr><tr>
	<td>config.id</td><td><code>number</code></td><td></td><td><p>The id of the added token.</p>
	</td>
	</tr><tr>
	<td>[config.single_word]</td><td><code>boolean</code></td><td><code>false</code></td><td><p>Whether this token must be a single word or can break words.</p>
	</td>
	</tr><tr>
	<td>[config.lstrip]</td><td><code>boolean</code></td><td><code>false</code></td><td><p>Whether this token should strip whitespaces on its left.</p>
	</td>
	</tr><tr>
	<td>[config.rstrip]</td><td><code>boolean</code></td><td><code>false</code></td><td><p>Whether this token should strip whitespaces on its right.</p>
	</td>
	</tr><tr>
	<td>[config.normalized]</td><td><code>boolean</code></td><td><code>false</code></td><td><p>Whether this token should be normalized.</p>
	</td>
	</tr><tr>
	<td>[config.special]</td><td><code>boolean</code></td><td><code>false</code></td><td><p>Whether this token is special.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..WordPieceTokenizer" class="group"></a>

	## tokenizers~WordPieceTokenizer ⇐ <code>TokenizerModel</code>

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

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>TokenizerModel</code>

	* [~WordPieceTokenizer](#module_tokenizers..WordPieceTokenizer) ⇐ <code>TokenizerModel</code>
	* [`new WordPieceTokenizer(config)`](#new_module_tokenizers..WordPieceTokenizer_new)
	* [`.tokens_to_ids`](#module_tokenizers..WordPieceTokenizer+tokens_to_ids) : <code>Map.<string, number></code>
	* [`.unk_token_id`](#module_tokenizers..WordPieceTokenizer+unk_token_id) : <code>number</code>
	* [`.unk_token`](#module_tokenizers..WordPieceTokenizer+unk_token) : <code>string</code>
	* [`.max_input_chars_per_word`](#module_tokenizers..WordPieceTokenizer+max_input_chars_per_word) : <code>number</code>
	* [`.vocab`](#module_tokenizers..WordPieceTokenizer+vocab) : <code>Array.<string></code>
	* [`.encode(tokens)`](#module_tokenizers..WordPieceTokenizer+encode) ⇒ <code>Array.<string></code>


	* * *

	<a id="new_module_tokenizers..WordPieceTokenizer_new" class="group"></a>

	### `new WordPieceTokenizer(config)`

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Default</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td></td><td><p>The configuration object.</p>
	</td>
	</tr><tr>
	<td>config.vocab</td><td><code>Object</code></td><td></td><td><p>A mapping of tokens to ids.</p>
	</td>
	</tr><tr>
	<td>config.unk_token</td><td><code>string</code></td><td></td><td><p>The unknown token string.</p>
	</td>
	</tr><tr>
	<td>config.continuing_subword_prefix</td><td><code>string</code></td><td></td><td><p>The prefix to use for continuing subwords.</p>
	</td>
	</tr><tr>
	<td>[config.max_input_chars_per_word]</td><td><code>number</code></td><td><code>100</code></td><td><p>The maximum number of characters per word.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..WordPieceTokenizer+tokens_to_ids" class="group"></a>

	### `wordPieceTokenizer.tokens_to_ids` : <code>Map.<string, number></code>

	A mapping of tokens to ids.

	Kind: instance property of [<code>WordPieceTokenizer</code>](#module_tokenizers..WordPieceTokenizer)

	* * *

	<a id="module_tokenizers..WordPieceTokenizer+unk_token_id" class="group"></a>

	### `wordPieceTokenizer.unk_token_id` : <code>number</code>

	The id of the unknown token.

	Kind: instance property of [<code>WordPieceTokenizer</code>](#module_tokenizers..WordPieceTokenizer)

	* * *

	<a id="module_tokenizers..WordPieceTokenizer+unk_token" class="group"></a>

	### `wordPieceTokenizer.unk_token` : <code>string</code>

	The unknown token string.

	Kind: instance property of [<code>WordPieceTokenizer</code>](#module_tokenizers..WordPieceTokenizer)

	* * *

	<a id="module_tokenizers..WordPieceTokenizer+max_input_chars_per_word" class="group"></a>

	### `wordPieceTokenizer.max_input_chars_per_word` : <code>number</code>

	The maximum number of characters allowed per word.

	Kind: instance property of [<code>WordPieceTokenizer</code>](#module_tokenizers..WordPieceTokenizer)

	* * *

	<a id="module_tokenizers..WordPieceTokenizer+vocab" class="group"></a>

	### `wordPieceTokenizer.vocab` : <code>Array.<string></code>

	An array of tokens.

	Kind: instance property of [<code>WordPieceTokenizer</code>](#module_tokenizers..WordPieceTokenizer)

	* * *

	<a id="module_tokenizers..WordPieceTokenizer+encode" class="group"></a>

	### `wordPieceTokenizer.encode(tokens)` ⇒ <code>Array.<string></code>

	Encodes an array of tokens using WordPiece encoding.

	Kind: instance method of [<code>WordPieceTokenizer</code>](#module_tokenizers..WordPieceTokenizer)
	Returns: <code>Array.<string></code> - An array of encoded tokens.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>tokens</td><td><code>Array.<string></code></td><td><p>The tokens to encode.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..Unigram" class="group"></a>

	## tokenizers~Unigram ⇐ <code>TokenizerModel</code>

	Class representing a Unigram tokenizer model.

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>TokenizerModel</code>

	* [~Unigram](#module_tokenizers..Unigram) ⇐ <code>TokenizerModel</code>
	* [`new Unigram(config, moreConfig)`](#new_module_tokenizers..Unigram_new)
	* [`.scores`](#module_tokenizers..Unigram+scores) : <code>Array.<number></code>
	* [`.populateNodes(lattice)`](#module_tokenizers..Unigram+populateNodes)
	* [`.tokenize(normalized)`](#module_tokenizers..Unigram+tokenize) ⇒ <code>Array.<string></code>
	* [`.encode(tokens)`](#module_tokenizers..Unigram+encode) ⇒ <code>Array.<string></code>


	* * *

	<a id="new_module_tokenizers..Unigram_new" class="group"></a>

	### `new Unigram(config, moreConfig)`

	Create a new Unigram tokenizer model.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration object for the Unigram model.</p>
	</td>
	</tr><tr>
	<td>config.unk_id</td><td><code>number</code></td><td><p>The ID of the unknown token</p>
	</td>
	</tr><tr>
	<td>config.vocab</td><td><code>*</code></td><td><p>A 2D array representing a mapping of tokens to scores.</p>
	</td>
	</tr><tr>
	<td>moreConfig</td><td><code>Object</code></td><td><p>Additional configuration object for the Unigram model.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..Unigram+scores" class="group"></a>

	### `unigram.scores` : <code>Array.<number></code>

	Kind: instance property of [<code>Unigram</code>](#module_tokenizers..Unigram)

	* * *

	<a id="module_tokenizers..Unigram+populateNodes" class="group"></a>

	### `unigram.populateNodes(lattice)`

	Populates lattice nodes.

	Kind: instance method of [<code>Unigram</code>](#module_tokenizers..Unigram)
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>lattice</td><td><code>TokenLattice</code></td><td><p>The token lattice to populate with nodes.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..Unigram+tokenize" class="group"></a>

	### `unigram.tokenize(normalized)` ⇒ <code>Array.<string></code>

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

	Kind: instance method of [<code>Unigram</code>](#module_tokenizers..Unigram)
	Returns: <code>Array.<string></code> - An array of subtokens obtained by encoding the input tokens using the unigram model.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>normalized</td><td><code>string</code></td><td><p>The normalized string.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..Unigram+encode" class="group"></a>

	### `unigram.encode(tokens)` ⇒ <code>Array.<string></code>

	Encodes an array of tokens using Unigram encoding.

	Kind: instance method of [<code>Unigram</code>](#module_tokenizers..Unigram)
	Returns: <code>Array.<string></code> - An array of encoded tokens.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>tokens</td><td><code>Array.<string></code></td><td><p>The tokens to encode.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..BPE" class="group"></a>

	## tokenizers~BPE ⇐ <code>TokenizerModel</code>

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

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>TokenizerModel</code>

	* [~BPE](#module_tokenizers..BPE) ⇐ <code>TokenizerModel</code>
	* [`new BPE(config)`](#new_module_tokenizers..BPE_new)
	* [`.tokens_to_ids`](#module_tokenizers..BPE+tokens_to_ids) : <code>Map.<string, number></code>
	* [`.merges`](#module_tokenizers..BPE+merges) : <code>*</code>
	* [`.config.merges`](#module_tokenizers..BPE+merges.config.merges) : <code>*</code>
	* [`.max_length_to_cache`](#module_tokenizers..BPE+max_length_to_cache)
	* [`.cache_capacity`](#module_tokenizers..BPE+cache_capacity)
	* [`.clear_cache()`](#module_tokenizers..BPE+clear_cache)
	* [`.bpe(token)`](#module_tokenizers..BPE+bpe) ⇒ <code>Array.<string></code>
	* [`.encode(tokens)`](#module_tokenizers..BPE+encode) ⇒ <code>Array.<string></code>


	* * *

	<a id="new_module_tokenizers..BPE_new" class="group"></a>

	### `new BPE(config)`

	Create a BPE instance.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Default</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td></td><td><p>The configuration object for BPE.</p>
	</td>
	</tr><tr>
	<td>config.vocab</td><td><code>Object</code></td><td></td><td><p>A mapping of tokens to ids.</p>
	</td>
	</tr><tr>
	<td>config.merges</td><td><code>*</code></td><td></td><td><p>An array of BPE merges as strings.</p>
	</td>
	</tr><tr>
	<td>config.unk_token</td><td><code>string</code></td><td></td><td><p>The unknown token used for out of vocabulary words.</p>
	</td>
	</tr><tr>
	<td>config.end_of_word_suffix</td><td><code>string</code></td><td></td><td><p>The suffix to place at the end of each word.</p>
	</td>
	</tr><tr>
	<td>[config.continuing_subword_suffix]</td><td><code>string</code></td><td></td><td><p>The suffix to insert between words.</p>
	</td>
	</tr><tr>
	<td>[config.byte_fallback]</td><td><code>boolean</code></td><td><code>false</code></td><td><p>Whether to use spm byte-fallback trick (defaults to False)</p>
	</td>
	</tr><tr>
	<td>[config.ignore_merges]</td><td><code>boolean</code></td><td><code>false</code></td><td><p>Whether or not to match tokens with the vocab before using merges.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..BPE+tokens_to_ids" class="group"></a>

	### `bpE.tokens_to_ids` : <code>Map.<string, number></code>

	Kind: instance property of [<code>BPE</code>](#module_tokenizers..BPE)

	* * *

	<a id="module_tokenizers..BPE+merges" class="group"></a>

	### `bpE.merges` : <code>*</code>

	Kind: instance property of [<code>BPE</code>](#module_tokenizers..BPE)

	* * *

	<a id="module_tokenizers..BPE+merges.config.merges" class="group"></a>

	#### `merges.config.merges` : <code>*</code>

	Kind: static property of [<code>merges</code>](#module_tokenizers..BPE+merges)

	* * *

	<a id="module_tokenizers..BPE+max_length_to_cache" class="group"></a>

	### `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 [<code>BPE</code>](#module_tokenizers..BPE)

	* * *

	<a id="module_tokenizers..BPE+cache_capacity" class="group"></a>

	### `bpE.cache_capacity`

	The default capacity for a `BPE`'s internal cache.

	Kind: instance property of [<code>BPE</code>](#module_tokenizers..BPE)

	* * *

	<a id="module_tokenizers..BPE+clear_cache" class="group"></a>

	### `bpE.clear_cache()`

	Clears the cache.

	Kind: instance method of [<code>BPE</code>](#module_tokenizers..BPE)

	* * *

	<a id="module_tokenizers..BPE+bpe" class="group"></a>

	### `bpE.bpe(token)` ⇒ <code>Array.<string></code>

	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 [<code>BPE</code>](#module_tokenizers..BPE)
	Returns: <code>Array.<string></code> - The BPE encoded tokens.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>token</td><td><code>string</code></td><td><p>The token to encode.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..BPE+encode" class="group"></a>

	### `bpE.encode(tokens)` ⇒ <code>Array.<string></code>

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

	Kind: instance method of [<code>BPE</code>](#module_tokenizers..BPE)
	Returns: <code>Array.<string></code> - The resulting subword tokens after applying the BPE algorithm to the input sequence of tokens.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>tokens</td><td><code>Array.<string></code></td><td><p>The input sequence of tokens to encode.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..LegacyTokenizerModel" class="group"></a>

	## tokenizers~LegacyTokenizerModel

	Legacy tokenizer class for tokenizers with only a vocabulary.

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)

	* [~LegacyTokenizerModel](#module_tokenizers..LegacyTokenizerModel)
	* [`new LegacyTokenizerModel(config, moreConfig)`](#new_module_tokenizers..LegacyTokenizerModel_new)
	* [`.tokens_to_ids`](#module_tokenizers..LegacyTokenizerModel+tokens_to_ids) : <code>Map.<string, number></code>


	* * *

	<a id="new_module_tokenizers..LegacyTokenizerModel_new" class="group"></a>

	### `new LegacyTokenizerModel(config, moreConfig)`

	Create a LegacyTokenizerModel instance.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration object for LegacyTokenizerModel.</p>
	</td>
	</tr><tr>
	<td>config.vocab</td><td><code>Object</code></td><td><p>A (possibly nested) mapping of tokens to ids.</p>
	</td>
	</tr><tr>
	<td>moreConfig</td><td><code>Object</code></td><td><p>Additional configuration object for the LegacyTokenizerModel model.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..LegacyTokenizerModel+tokens_to_ids" class="group"></a>

	### `legacyTokenizerModel.tokens_to_ids` : <code>Map.<string, number></code>

	Kind: instance property of [<code>LegacyTokenizerModel</code>](#module_tokenizers..LegacyTokenizerModel)

	* * *

	<a id="module_tokenizers..Normalizer" class="group"></a>

	## tokenizers~Normalizer

	A base class for text normalization.

	Kind: inner abstract class of [<code>tokenizers</code>](#module_tokenizers)

	* [~Normalizer](#module_tokenizers..Normalizer)
	* [`new Normalizer(config)`](#new_module_tokenizers..Normalizer_new)
	* _instance_
	* [`.normalize(text)`](#module_tokenizers..Normalizer+normalize) ⇒ <code>string</code>
	* [`._call(text)`](#module_tokenizers..Normalizer+_call) ⇒ <code>string</code>
	* _static_
	* [`.fromConfig(config)`](#module_tokenizers..Normalizer.fromConfig) ⇒ <code>Normalizer</code>


	* * *

	<a id="new_module_tokenizers..Normalizer_new" class="group"></a>

	### `new Normalizer(config)`

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration object for the normalizer.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..Normalizer+normalize" class="group"></a>

	### `normalizer.normalize(text)` ⇒ <code>string</code>

	Normalize the input text.

	Kind: instance abstract method of [<code>Normalizer</code>](#module_tokenizers..Normalizer)
	Returns: <code>string</code> - The normalized text.
	Throws:

	- <code>Error</code> If this method is not implemented in a subclass.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The text to normalize.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..Normalizer+_call" class="group"></a>

	### `normalizer._call(text)` ⇒ <code>string</code>

	Alias for [Normalizer#normalize](Normalizer#normalize).

	Kind: instance method of [<code>Normalizer</code>](#module_tokenizers..Normalizer)
	Returns: <code>string</code> - The normalized text.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The text to normalize.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..Normalizer.fromConfig" class="group"></a>

	### `Normalizer.fromConfig(config)` ⇒ <code>Normalizer</code>

	Factory method for creating normalizers from config objects.

	Kind: static method of [<code>Normalizer</code>](#module_tokenizers..Normalizer)
	Returns: <code>Normalizer</code> - A Normalizer object.
	Throws:

	- <code>Error</code> If an unknown Normalizer type is specified in the config.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration object for the normalizer.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..Replace" class="group"></a>

	## tokenizers~Replace ⇐ <code>Normalizer</code>

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

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>Normalizer</code>

	* * *

	<a id="module_tokenizers..Replace+normalize" class="group"></a>

	### `replace.normalize(text)` ⇒ <code>string</code>

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

	Kind: instance method of [<code>Replace</code>](#module_tokenizers..Replace)
	Returns: <code>string</code> - The normalized text after replacing the pattern with the content.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The input text to be normalized.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..UnicodeNormalizer" class="group"></a>

	## tokenizers~UnicodeNormalizer ⇐ <code>Normalizer</code>

	A normalizer that applies Unicode normalization to the input text.

	Kind: inner abstract class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>Normalizer</code>

	* [~UnicodeNormalizer](#module_tokenizers..UnicodeNormalizer) ⇐ <code>Normalizer</code>
	* [`.form`](#module_tokenizers..UnicodeNormalizer+form) : <code>string</code>
	* [`.normalize(text)`](#module_tokenizers..UnicodeNormalizer+normalize) ⇒ <code>string</code>


	* * *

	<a id="module_tokenizers..UnicodeNormalizer+form" class="group"></a>

	### `unicodeNormalizer.form` : <code>string</code>

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

	Kind: instance property of [<code>UnicodeNormalizer</code>](#module_tokenizers..UnicodeNormalizer)

	* * *

	<a id="module_tokenizers..UnicodeNormalizer+normalize" class="group"></a>

	### `unicodeNormalizer.normalize(text)` ⇒ <code>string</code>

	Normalize the input text by applying Unicode normalization.

	Kind: instance method of [<code>UnicodeNormalizer</code>](#module_tokenizers..UnicodeNormalizer)
	Returns: <code>string</code> - The normalized text.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The input text to be normalized.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..NFC" class="group"></a>

	## tokenizers~NFC ⇐ <code>UnicodeNormalizer</code>

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

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>UnicodeNormalizer</code>

	* * *

	<a id="module_tokenizers..NFD" class="group"></a>

	## tokenizers~NFD ⇐ <code>UnicodeNormalizer</code>

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

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>UnicodeNormalizer</code>

	* * *

	<a id="module_tokenizers..NFKC" class="group"></a>

	## tokenizers~NFKC ⇐ <code>UnicodeNormalizer</code>

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

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>UnicodeNormalizer</code>

	* * *

	<a id="module_tokenizers..NFKD" class="group"></a>

	## tokenizers~NFKD ⇐ <code>UnicodeNormalizer</code>

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

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>UnicodeNormalizer</code>

	* * *

	<a id="module_tokenizers..StripNormalizer" class="group"></a>

	## tokenizers~StripNormalizer

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

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)

	* * *

	<a id="module_tokenizers..StripNormalizer+normalize" class="group"></a>

	### `stripNormalizer.normalize(text)` ⇒ <code>string</code>

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

	Kind: instance method of [<code>StripNormalizer</code>](#module_tokenizers..StripNormalizer)
	Returns: <code>string</code> - The normalized text.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The input text.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..StripAccents" class="group"></a>

	## tokenizers~StripAccents ⇐ <code>Normalizer</code>

	StripAccents normalizer removes all accents from the text.

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>Normalizer</code>

	* * *

	<a id="module_tokenizers..StripAccents+normalize" class="group"></a>

	### `stripAccents.normalize(text)` ⇒ <code>string</code>

	Remove all accents from the text.

	Kind: instance method of [<code>StripAccents</code>](#module_tokenizers..StripAccents)
	Returns: <code>string</code> - The normalized text without accents.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The input text.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..Lowercase" class="group"></a>

	## tokenizers~Lowercase ⇐ <code>Normalizer</code>

	A Normalizer that lowercases the input string.

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>Normalizer</code>

	* * *

	<a id="module_tokenizers..Lowercase+normalize" class="group"></a>

	### `lowercase.normalize(text)` ⇒ <code>string</code>

	Lowercases the input string.

	Kind: instance method of [<code>Lowercase</code>](#module_tokenizers..Lowercase)
	Returns: <code>string</code> - The normalized text.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The text to normalize.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..Prepend" class="group"></a>

	## tokenizers~Prepend ⇐ <code>Normalizer</code>

	A Normalizer that prepends a string to the input string.

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>Normalizer</code>

	* * *

	<a id="module_tokenizers..Prepend+normalize" class="group"></a>

	### `prepend.normalize(text)` ⇒ <code>string</code>

	Prepends the input string.

	Kind: instance method of [<code>Prepend</code>](#module_tokenizers..Prepend)
	Returns: <code>string</code> - The normalized text.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The text to normalize.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..NormalizerSequence" class="group"></a>

	## tokenizers~NormalizerSequence ⇐ <code>Normalizer</code>

	A Normalizer that applies a sequence of Normalizers.

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>Normalizer</code>

	* [~NormalizerSequence](#module_tokenizers..NormalizerSequence) ⇐ <code>Normalizer</code>
	* [`new NormalizerSequence(config)`](#new_module_tokenizers..NormalizerSequence_new)
	* [`.normalize(text)`](#module_tokenizers..NormalizerSequence+normalize) ⇒ <code>string</code>


	* * *

	<a id="new_module_tokenizers..NormalizerSequence_new" class="group"></a>

	### `new NormalizerSequence(config)`

	Create a new instance of NormalizerSequence.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration object.</p>
	</td>
	</tr><tr>
	<td>config.normalizers</td><td><code>Array.<Object></code></td><td><p>An array of Normalizer configuration objects.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..NormalizerSequence+normalize" class="group"></a>

	### `normalizerSequence.normalize(text)` ⇒ <code>string</code>

	Apply a sequence of Normalizers to the input text.

	Kind: instance method of [<code>NormalizerSequence</code>](#module_tokenizers..NormalizerSequence)
	Returns: <code>string</code> - The normalized text.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The text to normalize.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..BertNormalizer" class="group"></a>

	## tokenizers~BertNormalizer ⇐ <code>Normalizer</code>

	A class representing a normalizer used in BERT tokenization.

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>Normalizer</code>

	* [~BertNormalizer](#module_tokenizers..BertNormalizer) ⇐ <code>Normalizer</code>
	* [`._tokenize_chinese_chars(text)`](#module_tokenizers..BertNormalizer+_tokenize_chinese_chars) ⇒ <code>string</code>
	* [`.stripAccents(text)`](#module_tokenizers..BertNormalizer+stripAccents) ⇒ <code>string</code>
	* [`.normalize(text)`](#module_tokenizers..BertNormalizer+normalize) ⇒ <code>string</code>


	* * *

	<a id="module_tokenizers..BertNormalizer+_tokenize_chinese_chars" class="group"></a>

	### `bertNormalizer._tokenize_chinese_chars(text)` ⇒ <code>string</code>

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

	Kind: instance method of [<code>BertNormalizer</code>](#module_tokenizers..BertNormalizer)
	Returns: <code>string</code> - The tokenized text with whitespace added around CJK characters.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The input text to tokenize.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..BertNormalizer+stripAccents" class="group"></a>

	### `bertNormalizer.stripAccents(text)` ⇒ <code>string</code>

	Strips accents from the given text.

	Kind: instance method of [<code>BertNormalizer</code>](#module_tokenizers..BertNormalizer)
	Returns: <code>string</code> - The text with accents removed.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The text to strip accents from.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..BertNormalizer+normalize" class="group"></a>

	### `bertNormalizer.normalize(text)` ⇒ <code>string</code>

	Normalizes the given text based on the configuration.

	Kind: instance method of [<code>BertNormalizer</code>](#module_tokenizers..BertNormalizer)
	Returns: <code>string</code> - The normalized text.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The text to normalize.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..PreTokenizer" class="group"></a>

	## tokenizers~PreTokenizer ⇐ [<code>Callable</code>](#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 [<code>tokenizers</code>](#module_tokenizers)
	Extends: [<code>Callable</code>](#Callable)

	* [~PreTokenizer](#module_tokenizers..PreTokenizer) ⇐ [<code>Callable</code>](#Callable)
	* _instance_
	* [`.pre_tokenize_text(text, [options])`](#module_tokenizers..PreTokenizer+pre_tokenize_text) ⇒ <code>Array.<string></code>
	* [`.pre_tokenize(text, [options])`](#module_tokenizers..PreTokenizer+pre_tokenize) ⇒ <code>Array.<string></code>
	* [`._call(text, [options])`](#module_tokenizers..PreTokenizer+_call) ⇒ <code>Array.<string></code>
	* _static_
	* [`.fromConfig(config)`](#module_tokenizers..PreTokenizer.fromConfig) ⇒ <code>PreTokenizer</code>


	* * *

	<a id="module_tokenizers..PreTokenizer+pre_tokenize_text" class="group"></a>

	### `preTokenizer.pre_tokenize_text(text, [options])` ⇒ <code>Array.<string></code>

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

	Kind: instance abstract method of [<code>PreTokenizer</code>](#module_tokenizers..PreTokenizer)
	Returns: <code>Array.<string></code> - The pre-tokenized text.
	Throws:

	- <code>Error</code> If the method is not implemented in the subclass.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The text to pre-tokenize.</p>
	</td>
	</tr><tr>
	<td>[options]</td><td><code>Object</code></td><td><p>Additional options for the pre-tokenization logic.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..PreTokenizer+pre_tokenize" class="group"></a>

	### `preTokenizer.pre_tokenize(text, [options])` ⇒ <code>Array.<string></code>

	Tokenizes the given text into pre-tokens.

	Kind: instance method of [<code>PreTokenizer</code>](#module_tokenizers..PreTokenizer)
	Returns: <code>Array.<string></code> - An array of pre-tokens.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code> \| <code>Array<string></code></td><td><p>The text or array of texts to pre-tokenize.</p>
	</td>
	</tr><tr>
	<td>[options]</td><td><code>Object</code></td><td><p>Additional options for the pre-tokenization logic.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..PreTokenizer+_call" class="group"></a>

	### `preTokenizer._call(text, [options])` ⇒ <code>Array.<string></code>

	Alias for [PreTokenizer#pre_tokenize](PreTokenizer#pre_tokenize).

	Kind: instance method of [<code>PreTokenizer</code>](#module_tokenizers..PreTokenizer)
	Overrides: [<code>_call</code>](#Callable+_call)
	Returns: <code>Array.<string></code> - An array of pre-tokens.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code> \| <code>Array<string></code></td><td><p>The text or array of texts to pre-tokenize.</p>
	</td>
	</tr><tr>
	<td>[options]</td><td><code>Object</code></td><td><p>Additional options for the pre-tokenization logic.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..PreTokenizer.fromConfig" class="group"></a>

	### `PreTokenizer.fromConfig(config)` ⇒ <code>PreTokenizer</code>

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

	Kind: static method of [<code>PreTokenizer</code>](#module_tokenizers..PreTokenizer)
	Returns: <code>PreTokenizer</code> - An instance of a subclass of `PreTokenizer`.
	Throws:

	- <code>Error</code> If the provided configuration object does not correspond to any known pre-tokenizer.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>A configuration object for the pre-tokenizer.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..BertPreTokenizer" class="group"></a>

	## tokenizers~BertPreTokenizer ⇐ <code>PreTokenizer</code>

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>PreTokenizer</code>

	* [~BertPreTokenizer](#module_tokenizers..BertPreTokenizer) ⇐ <code>PreTokenizer</code>
	* [`new BertPreTokenizer(config)`](#new_module_tokenizers..BertPreTokenizer_new)
	* [`.pre_tokenize_text(text, [options])`](#module_tokenizers..BertPreTokenizer+pre_tokenize_text) ⇒ <code>Array.<string></code>


	* * *

	<a id="new_module_tokenizers..BertPreTokenizer_new" class="group"></a>

	### `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.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration object.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..BertPreTokenizer+pre_tokenize_text" class="group"></a>

	### `bertPreTokenizer.pre_tokenize_text(text, [options])` ⇒ <code>Array.<string></code>

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

	Kind: instance method of [<code>BertPreTokenizer</code>](#module_tokenizers..BertPreTokenizer)
	Returns: <code>Array.<string></code> - An array of tokens.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The text to tokenize.</p>
	</td>
	</tr><tr>
	<td>[options]</td><td><code>Object</code></td><td><p>Additional options for the pre-tokenization logic.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..ByteLevelPreTokenizer" class="group"></a>

	## tokenizers~ByteLevelPreTokenizer ⇐ <code>PreTokenizer</code>

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

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>PreTokenizer</code>

	* [~ByteLevelPreTokenizer](#module_tokenizers..ByteLevelPreTokenizer) ⇐ <code>PreTokenizer</code>
	* [`new ByteLevelPreTokenizer(config)`](#new_module_tokenizers..ByteLevelPreTokenizer_new)
	* [`.add_prefix_space`](#module_tokenizers..ByteLevelPreTokenizer+add_prefix_space) : <code>boolean</code>
	* [`.trim_offsets`](#module_tokenizers..ByteLevelPreTokenizer+trim_offsets) : <code>boolean</code>
	* [`.use_regex`](#module_tokenizers..ByteLevelPreTokenizer+use_regex) : <code>boolean</code>
	* [`.pre_tokenize_text(text, [options])`](#module_tokenizers..ByteLevelPreTokenizer+pre_tokenize_text) ⇒ <code>Array.<string></code>


	* * *

	<a id="new_module_tokenizers..ByteLevelPreTokenizer_new" class="group"></a>

	### `new ByteLevelPreTokenizer(config)`

	Creates a new instance of the `ByteLevelPreTokenizer` class.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration object.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..ByteLevelPreTokenizer+add_prefix_space" class="group"></a>

	### `byteLevelPreTokenizer.add_prefix_space` : <code>boolean</code>

	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 [<code>ByteLevelPreTokenizer</code>](#module_tokenizers..ByteLevelPreTokenizer)

	* * *

	<a id="module_tokenizers..ByteLevelPreTokenizer+trim_offsets" class="group"></a>

	### `byteLevelPreTokenizer.trim_offsets` : <code>boolean</code>

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

	Kind: instance property of [<code>ByteLevelPreTokenizer</code>](#module_tokenizers..ByteLevelPreTokenizer)
	Todo

	- Use this in the pretokenization step.


	* * *

	<a id="module_tokenizers..ByteLevelPreTokenizer+use_regex" class="group"></a>

	### `byteLevelPreTokenizer.use_regex` : <code>boolean</code>

	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 [<code>ByteLevelPreTokenizer</code>](#module_tokenizers..ByteLevelPreTokenizer)

	* * *

	<a id="module_tokenizers..ByteLevelPreTokenizer+pre_tokenize_text" class="group"></a>

	### `byteLevelPreTokenizer.pre_tokenize_text(text, [options])` ⇒ <code>Array.<string></code>

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

	Kind: instance method of [<code>ByteLevelPreTokenizer</code>](#module_tokenizers..ByteLevelPreTokenizer)
	Returns: <code>Array.<string></code> - An array of tokens.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The text to tokenize.</p>
	</td>
	</tr><tr>
	<td>[options]</td><td><code>Object</code></td><td><p>Additional options for the pre-tokenization logic.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..SplitPreTokenizer" class="group"></a>

	## tokenizers~SplitPreTokenizer ⇐ <code>PreTokenizer</code>

	Splits text using a given pattern.

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>PreTokenizer</code>

	* [~SplitPreTokenizer](#module_tokenizers..SplitPreTokenizer) ⇐ <code>PreTokenizer</code>
	* [`new SplitPreTokenizer(config)`](#new_module_tokenizers..SplitPreTokenizer_new)
	* [`.pre_tokenize_text(text, [options])`](#module_tokenizers..SplitPreTokenizer+pre_tokenize_text) ⇒ <code>Array.<string></code>


	* * *

	<a id="new_module_tokenizers..SplitPreTokenizer_new" class="group"></a>

	### `new SplitPreTokenizer(config)`

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration options for the pre-tokenizer.</p>
	</td>
	</tr><tr>
	<td>config.pattern</td><td><code>Object</code></td><td><p>The pattern used to split the text. Can be a string or a regex object.</p>
	</td>
	</tr><tr>
	<td>config.pattern.String</td><td><code>string</code> \| <code>undefined</code></td><td><p>The string to use for splitting. Only defined if the pattern is a string.</p>
	</td>
	</tr><tr>
	<td>config.pattern.Regex</td><td><code>string</code> \| <code>undefined</code></td><td><p>The regex to use for splitting. Only defined if the pattern is a regex.</p>
	</td>
	</tr><tr>
	<td>config.behavior</td><td><code>SplitDelimiterBehavior</code></td><td><p>The behavior to use when splitting.</p>
	</td>
	</tr><tr>
	<td>config.invert</td><td><code>boolean</code></td><td><p>Whether to split (invert=false) or match (invert=true) the pattern.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..SplitPreTokenizer+pre_tokenize_text" class="group"></a>

	### `splitPreTokenizer.pre_tokenize_text(text, [options])` ⇒ <code>Array.<string></code>

	Tokenizes text by splitting it using the given pattern.

	Kind: instance method of [<code>SplitPreTokenizer</code>](#module_tokenizers..SplitPreTokenizer)
	Returns: <code>Array.<string></code> - An array of tokens.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The text to tokenize.</p>
	</td>
	</tr><tr>
	<td>[options]</td><td><code>Object</code></td><td><p>Additional options for the pre-tokenization logic.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..PunctuationPreTokenizer" class="group"></a>

	## tokenizers~PunctuationPreTokenizer ⇐ <code>PreTokenizer</code>

	Splits text based on punctuation.

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>PreTokenizer</code>

	* [~PunctuationPreTokenizer](#module_tokenizers..PunctuationPreTokenizer) ⇐ <code>PreTokenizer</code>
	* [`new PunctuationPreTokenizer(config)`](#new_module_tokenizers..PunctuationPreTokenizer_new)
	* [`.pre_tokenize_text(text, [options])`](#module_tokenizers..PunctuationPreTokenizer+pre_tokenize_text) ⇒ <code>Array.<string></code>


	* * *

	<a id="new_module_tokenizers..PunctuationPreTokenizer_new" class="group"></a>

	### `new PunctuationPreTokenizer(config)`

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration options for the pre-tokenizer.</p>
	</td>
	</tr><tr>
	<td>config.behavior</td><td><code>SplitDelimiterBehavior</code></td><td><p>The behavior to use when splitting.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..PunctuationPreTokenizer+pre_tokenize_text" class="group"></a>

	### `punctuationPreTokenizer.pre_tokenize_text(text, [options])` ⇒ <code>Array.<string></code>

	Tokenizes text by splitting it using the given pattern.

	Kind: instance method of [<code>PunctuationPreTokenizer</code>](#module_tokenizers..PunctuationPreTokenizer)
	Returns: <code>Array.<string></code> - An array of tokens.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The text to tokenize.</p>
	</td>
	</tr><tr>
	<td>[options]</td><td><code>Object</code></td><td><p>Additional options for the pre-tokenization logic.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..DigitsPreTokenizer" class="group"></a>

	## tokenizers~DigitsPreTokenizer ⇐ <code>PreTokenizer</code>

	Splits text based on digits.

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>PreTokenizer</code>

	* [~DigitsPreTokenizer](#module_tokenizers..DigitsPreTokenizer) ⇐ <code>PreTokenizer</code>
	* [`new DigitsPreTokenizer(config)`](#new_module_tokenizers..DigitsPreTokenizer_new)
	* [`.pre_tokenize_text(text, [options])`](#module_tokenizers..DigitsPreTokenizer+pre_tokenize_text) ⇒ <code>Array.<string></code>


	* * *

	<a id="new_module_tokenizers..DigitsPreTokenizer_new" class="group"></a>

	### `new DigitsPreTokenizer(config)`

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration options for the pre-tokenizer.</p>
	</td>
	</tr><tr>
	<td>config.individual_digits</td><td><code>boolean</code></td><td><p>Whether to split on individual digits.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..DigitsPreTokenizer+pre_tokenize_text" class="group"></a>

	### `digitsPreTokenizer.pre_tokenize_text(text, [options])` ⇒ <code>Array.<string></code>

	Tokenizes text by splitting it using the given pattern.

	Kind: instance method of [<code>DigitsPreTokenizer</code>](#module_tokenizers..DigitsPreTokenizer)
	Returns: <code>Array.<string></code> - An array of tokens.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The text to tokenize.</p>
	</td>
	</tr><tr>
	<td>[options]</td><td><code>Object</code></td><td><p>Additional options for the pre-tokenization logic.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..PostProcessor" class="group"></a>

	## tokenizers~PostProcessor ⇐ [<code>Callable</code>](#Callable)

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: [<code>Callable</code>](#Callable)

	* [~PostProcessor](#module_tokenizers..PostProcessor) ⇐ [<code>Callable</code>](#Callable)
	* [`new PostProcessor(config)`](#new_module_tokenizers..PostProcessor_new)
	* _instance_
	* [`.post_process(tokens, ...args)`](#module_tokenizers..PostProcessor+post_process) ⇒ <code>PostProcessedOutput</code>
	* [`._call(tokens, ...args)`](#module_tokenizers..PostProcessor+_call) ⇒ <code>PostProcessedOutput</code>
	* _static_
	* [`.fromConfig(config)`](#module_tokenizers..PostProcessor.fromConfig) ⇒ <code>PostProcessor</code>


	* * *

	<a id="new_module_tokenizers..PostProcessor_new" class="group"></a>

	### `new PostProcessor(config)`

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration for the post-processor.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..PostProcessor+post_process" class="group"></a>

	### `postProcessor.post_process(tokens, ...args)` ⇒ <code>PostProcessedOutput</code>

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

	Kind: instance method of [<code>PostProcessor</code>](#module_tokenizers..PostProcessor)
	Returns: <code>PostProcessedOutput</code> - The post-processed tokens.
	Throws:

	- <code>Error</code> If the method is not implemented in subclass.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>tokens</td><td><code>Array</code></td><td><p>The input tokens to be post-processed.</p>
	</td>
	</tr><tr>
	<td>...args</td><td><code>*</code></td><td><p>Additional arguments required by the post-processing logic.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..PostProcessor+_call" class="group"></a>

	### `postProcessor._call(tokens, ...args)` ⇒ <code>PostProcessedOutput</code>

	Alias for [PostProcessor#post_process](PostProcessor#post_process).

	Kind: instance method of [<code>PostProcessor</code>](#module_tokenizers..PostProcessor)
	Overrides: [<code>_call</code>](#Callable+_call)
	Returns: <code>PostProcessedOutput</code> - The post-processed tokens.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>tokens</td><td><code>Array</code></td><td><p>The text or array of texts to post-process.</p>
	</td>
	</tr><tr>
	<td>...args</td><td><code>*</code></td><td><p>Additional arguments required by the post-processing logic.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..PostProcessor.fromConfig" class="group"></a>

	### `PostProcessor.fromConfig(config)` ⇒ <code>PostProcessor</code>

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

	Kind: static method of [<code>PostProcessor</code>](#module_tokenizers..PostProcessor)
	Returns: <code>PostProcessor</code> - A PostProcessor object created from the given configuration.
	Throws:

	- <code>Error</code> If an unknown PostProcessor type is encountered.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>Configuration object representing a PostProcessor.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..BertProcessing" class="group"></a>

	## tokenizers~BertProcessing

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

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)

	* [~BertProcessing](#module_tokenizers..BertProcessing)
	* [`new BertProcessing(config)`](#new_module_tokenizers..BertProcessing_new)
	* [`.post_process(tokens, [tokens_pair])`](#module_tokenizers..BertProcessing+post_process) ⇒ <code>PostProcessedOutput</code>


	* * *

	<a id="new_module_tokenizers..BertProcessing_new" class="group"></a>

	### `new BertProcessing(config)`

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration for the post-processor.</p>
	</td>
	</tr><tr>
	<td>config.cls</td><td><code>Array.<string></code></td><td><p>The special tokens to add to the beginning of the input.</p>
	</td>
	</tr><tr>
	<td>config.sep</td><td><code>Array.<string></code></td><td><p>The special tokens to add to the end of the input.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..BertProcessing+post_process" class="group"></a>

	### `bertProcessing.post_process(tokens, [tokens_pair])` ⇒ <code>PostProcessedOutput</code>

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

	Kind: instance method of [<code>BertProcessing</code>](#module_tokenizers..BertProcessing)
	Returns: <code>PostProcessedOutput</code> - The post-processed tokens with the special tokens added to the beginning and end.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Default</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>tokens</td><td><code>Array.<string></code></td><td></td><td><p>The input tokens.</p>
	</td>
	</tr><tr>
	<td>[tokens_pair]</td><td><code>Array.<string></code></td><td><code></code></td><td><p>An optional second set of input tokens.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..TemplateProcessing" class="group"></a>

	## tokenizers~TemplateProcessing ⇐ <code>PostProcessor</code>

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

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>PostProcessor</code>

	* [~TemplateProcessing](#module_tokenizers..TemplateProcessing) ⇐ <code>PostProcessor</code>
	* [`new TemplateProcessing(config)`](#new_module_tokenizers..TemplateProcessing_new)
	* [`.post_process(tokens, [tokens_pair])`](#module_tokenizers..TemplateProcessing+post_process) ⇒ <code>PostProcessedOutput</code>


	* * *

	<a id="new_module_tokenizers..TemplateProcessing_new" class="group"></a>

	### `new TemplateProcessing(config)`

	Creates a new instance of `TemplateProcessing`.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration options for the post processor.</p>
	</td>
	</tr><tr>
	<td>config.single</td><td><code>Array</code></td><td><p>The template for a single sequence of tokens.</p>
	</td>
	</tr><tr>
	<td>config.pair</td><td><code>Array</code></td><td><p>The template for a pair of sequences of tokens.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..TemplateProcessing+post_process" class="group"></a>

	### `templateProcessing.post_process(tokens, [tokens_pair])` ⇒ <code>PostProcessedOutput</code>

	Replaces special tokens in the template with actual tokens.

	Kind: instance method of [<code>TemplateProcessing</code>](#module_tokenizers..TemplateProcessing)
	Returns: <code>PostProcessedOutput</code> - An object containing the list of tokens with the special tokens replaced with actual tokens.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Default</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>tokens</td><td><code>Array.<string></code></td><td></td><td><p>The list of tokens for the first sequence.</p>
	</td>
	</tr><tr>
	<td>[tokens_pair]</td><td><code>Array.<string></code></td><td><code></code></td><td><p>The list of tokens for the second sequence (optional).</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..ByteLevelPostProcessor" class="group"></a>

	## tokenizers~ByteLevelPostProcessor ⇐ <code>PostProcessor</code>

	A PostProcessor that returns the given tokens as is.

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>PostProcessor</code>

	* * *

	<a id="module_tokenizers..ByteLevelPostProcessor+post_process" class="group"></a>

	### `byteLevelPostProcessor.post_process(tokens, [tokens_pair])` ⇒ <code>PostProcessedOutput</code>

	Post process the given tokens.

	Kind: instance method of [<code>ByteLevelPostProcessor</code>](#module_tokenizers..ByteLevelPostProcessor)
	Returns: <code>PostProcessedOutput</code> - An object containing the post-processed tokens.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Default</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>tokens</td><td><code>Array.<string></code></td><td></td><td><p>The list of tokens for the first sequence.</p>
	</td>
	</tr><tr>
	<td>[tokens_pair]</td><td><code>Array.<string></code></td><td><code></code></td><td><p>The list of tokens for the second sequence (optional).</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..PostProcessorSequence" class="group"></a>

	## tokenizers~PostProcessorSequence

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

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)

	* [~PostProcessorSequence](#module_tokenizers..PostProcessorSequence)
	* [`new PostProcessorSequence(config)`](#new_module_tokenizers..PostProcessorSequence_new)
	* [`.post_process(tokens, [tokens_pair])`](#module_tokenizers..PostProcessorSequence+post_process) ⇒ <code>PostProcessedOutput</code>


	* * *

	<a id="new_module_tokenizers..PostProcessorSequence_new" class="group"></a>

	### `new PostProcessorSequence(config)`

	Creates a new instance of PostProcessorSequence.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration object.</p>
	</td>
	</tr><tr>
	<td>config.processors</td><td><code>Array.<Object></code></td><td><p>The list of post-processors to apply.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..PostProcessorSequence+post_process" class="group"></a>

	### `postProcessorSequence.post_process(tokens, [tokens_pair])` ⇒ <code>PostProcessedOutput</code>

	Post process the given tokens.

	Kind: instance method of [<code>PostProcessorSequence</code>](#module_tokenizers..PostProcessorSequence)
	Returns: <code>PostProcessedOutput</code> - An object containing the post-processed tokens.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Default</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>tokens</td><td><code>Array.<string></code></td><td></td><td><p>The list of tokens for the first sequence.</p>
	</td>
	</tr><tr>
	<td>[tokens_pair]</td><td><code>Array.<string></code></td><td><code></code></td><td><p>The list of tokens for the second sequence (optional).</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..Decoder" class="group"></a>

	## tokenizers~Decoder ⇐ [<code>Callable</code>](#Callable)

	The base class for token decoders.

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: [<code>Callable</code>](#Callable)

	* [~Decoder](#module_tokenizers..Decoder) ⇐ [<code>Callable</code>](#Callable)
	* [`new Decoder(config)`](#new_module_tokenizers..Decoder_new)
	* _instance_
	* [`.added_tokens`](#module_tokenizers..Decoder+added_tokens) : <code>Array.<AddedToken></code>
	* [`._call(tokens)`](#module_tokenizers..Decoder+_call) ⇒ <code>string</code>
	* [`.decode(tokens)`](#module_tokenizers..Decoder+decode) ⇒ <code>string</code>
	* [`.decode_chain(tokens)`](#module_tokenizers..Decoder+decode_chain) ⇒ <code>Array.<string></code>
	* _static_
	* [`.fromConfig(config)`](#module_tokenizers..Decoder.fromConfig) ⇒ <code>Decoder</code>


	* * *

	<a id="new_module_tokenizers..Decoder_new" class="group"></a>

	### `new Decoder(config)`

	Creates an instance of `Decoder`.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration object.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..Decoder+added_tokens" class="group"></a>

	### `decoder.added_tokens` : <code>Array.<AddedToken></code>

	Kind: instance property of [<code>Decoder</code>](#module_tokenizers..Decoder)

	* * *

	<a id="module_tokenizers..Decoder+_call" class="group"></a>

	### `decoder._call(tokens)` ⇒ <code>string</code>

	Calls the `decode` method.

	Kind: instance method of [<code>Decoder</code>](#module_tokenizers..Decoder)
	Overrides: [<code>_call</code>](#Callable+_call)
	Returns: <code>string</code> - The decoded string.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>tokens</td><td><code>Array.<string></code></td><td><p>The list of tokens.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..Decoder+decode" class="group"></a>

	### `decoder.decode(tokens)` ⇒ <code>string</code>

	Decodes a list of tokens.

	Kind: instance method of [<code>Decoder</code>](#module_tokenizers..Decoder)
	Returns: <code>string</code> - The decoded string.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>tokens</td><td><code>Array.<string></code></td><td><p>The list of tokens.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..Decoder+decode_chain" class="group"></a>

	### `decoder.decode_chain(tokens)` ⇒ <code>Array.<string></code>

	Apply the decoder to a list of tokens.

	Kind: instance method of [<code>Decoder</code>](#module_tokenizers..Decoder)
	Returns: <code>Array.<string></code> - The decoded list of tokens.
	Throws:

	- <code>Error</code> If the `decode_chain` method is not implemented in the subclass.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>tokens</td><td><code>Array.<string></code></td><td><p>The list of tokens.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..Decoder.fromConfig" class="group"></a>

	### `Decoder.fromConfig(config)` ⇒ <code>Decoder</code>

	Creates a decoder instance based on the provided configuration.

	Kind: static method of [<code>Decoder</code>](#module_tokenizers..Decoder)
	Returns: <code>Decoder</code> - A decoder instance.
	Throws:

	- <code>Error</code> If an unknown decoder type is provided.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration object.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..FuseDecoder" class="group"></a>

	## 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 [<code>tokenizers</code>](#module_tokenizers)

	* * *

	<a id="module_tokenizers..FuseDecoder+decode_chain" class="group"></a>

	### `fuseDecoder.decode_chain()` : <code>*</code>

	Kind: instance method of [<code>FuseDecoder</code>](#module_tokenizers..FuseDecoder)

	* * *

	<a id="module_tokenizers..WordPieceDecoder" class="group"></a>

	## tokenizers~WordPieceDecoder ⇐ <code>Decoder</code>

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

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>Decoder</code>

	* [~WordPieceDecoder](#module_tokenizers..WordPieceDecoder) ⇐ <code>Decoder</code>
	* [`new WordPieceDecoder(config)`](#new_module_tokenizers..WordPieceDecoder_new)
	* [`.decode_chain()`](#module_tokenizers..WordPieceDecoder+decode_chain) : <code>*</code>


	* * *

	<a id="new_module_tokenizers..WordPieceDecoder_new" class="group"></a>

	### `new WordPieceDecoder(config)`

	Creates a new instance of WordPieceDecoder.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration object.</p>
	</td>
	</tr><tr>
	<td>config.prefix</td><td><code>string</code></td><td><p>The prefix used for WordPiece encoding.</p>
	</td>
	</tr><tr>
	<td>config.cleanup</td><td><code>boolean</code></td><td><p>Whether to cleanup the decoded string.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..WordPieceDecoder+decode_chain" class="group"></a>

	### `wordPieceDecoder.decode_chain()` : <code>*</code>

	Kind: instance method of [<code>WordPieceDecoder</code>](#module_tokenizers..WordPieceDecoder)

	* * *

	<a id="module_tokenizers..ByteLevelDecoder" class="group"></a>

	## tokenizers~ByteLevelDecoder ⇐ <code>Decoder</code>

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

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>Decoder</code>

	* [~ByteLevelDecoder](#module_tokenizers..ByteLevelDecoder) ⇐ <code>Decoder</code>
	* [`new ByteLevelDecoder(config)`](#new_module_tokenizers..ByteLevelDecoder_new)
	* [`.convert_tokens_to_string(tokens)`](#module_tokenizers..ByteLevelDecoder+convert_tokens_to_string) ⇒ <code>string</code>
	* [`.decode_chain()`](#module_tokenizers..ByteLevelDecoder+decode_chain) : <code>*</code>


	* * *

	<a id="new_module_tokenizers..ByteLevelDecoder_new" class="group"></a>

	### `new ByteLevelDecoder(config)`

	Create a `ByteLevelDecoder` object.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>Configuration object.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..ByteLevelDecoder+convert_tokens_to_string" class="group"></a>

	### `byteLevelDecoder.convert_tokens_to_string(tokens)` ⇒ <code>string</code>

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

	Kind: instance method of [<code>ByteLevelDecoder</code>](#module_tokenizers..ByteLevelDecoder)
	Returns: <code>string</code> - The decoded string.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>tokens</td><td><code>Array.<string></code></td><td><p>Array of tokens to be decoded.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..ByteLevelDecoder+decode_chain" class="group"></a>

	### `byteLevelDecoder.decode_chain()` : <code>*</code>

	Kind: instance method of [<code>ByteLevelDecoder</code>](#module_tokenizers..ByteLevelDecoder)

	* * *

	<a id="module_tokenizers..CTCDecoder" class="group"></a>

	## 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 [<code>tokenizers</code>](#module_tokenizers)

	* [~CTCDecoder](#module_tokenizers..CTCDecoder)
	* [`.convert_tokens_to_string(tokens)`](#module_tokenizers..CTCDecoder+convert_tokens_to_string) ⇒ <code>string</code>
	* [`.decode_chain()`](#module_tokenizers..CTCDecoder+decode_chain) : <code>*</code>


	* * *

	<a id="module_tokenizers..CTCDecoder+convert_tokens_to_string" class="group"></a>

	### `ctcDecoder.convert_tokens_to_string(tokens)` ⇒ <code>string</code>

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

	Kind: instance method of [<code>CTCDecoder</code>](#module_tokenizers..CTCDecoder)
	Returns: <code>string</code> - The decoded string.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>tokens</td><td><code>Array.<string></code></td><td><p>Array of tokens to be decoded.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..CTCDecoder+decode_chain" class="group"></a>

	### `ctcDecoder.decode_chain()` : <code>*</code>

	Kind: instance method of [<code>CTCDecoder</code>](#module_tokenizers..CTCDecoder)

	* * *

	<a id="module_tokenizers..DecoderSequence" class="group"></a>

	## tokenizers~DecoderSequence ⇐ <code>Decoder</code>

	Apply a sequence of decoders.

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>Decoder</code>

	* [~DecoderSequence](#module_tokenizers..DecoderSequence) ⇐ <code>Decoder</code>
	* [`new DecoderSequence(config)`](#new_module_tokenizers..DecoderSequence_new)
	* [`.decode_chain()`](#module_tokenizers..DecoderSequence+decode_chain) : <code>*</code>


	* * *

	<a id="new_module_tokenizers..DecoderSequence_new" class="group"></a>

	### `new DecoderSequence(config)`

	Creates a new instance of DecoderSequence.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration object.</p>
	</td>
	</tr><tr>
	<td>config.decoders</td><td><code>Array.<Object></code></td><td><p>The list of decoders to apply.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..DecoderSequence+decode_chain" class="group"></a>

	### `decoderSequence.decode_chain()` : <code>*</code>

	Kind: instance method of [<code>DecoderSequence</code>](#module_tokenizers..DecoderSequence)

	* * *

	<a id="module_tokenizers..MetaspacePreTokenizer" class="group"></a>

	## tokenizers~MetaspacePreTokenizer ⇐ <code>PreTokenizer</code>

	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 [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>PreTokenizer</code>

	* [~MetaspacePreTokenizer](#module_tokenizers..MetaspacePreTokenizer) ⇐ <code>PreTokenizer</code>
	* [`new MetaspacePreTokenizer(config)`](#new_module_tokenizers..MetaspacePreTokenizer_new)
	* [`.pre_tokenize_text(text, [options])`](#module_tokenizers..MetaspacePreTokenizer+pre_tokenize_text) ⇒ <code>Array.<string></code>


	* * *

	<a id="new_module_tokenizers..MetaspacePreTokenizer_new" class="group"></a>

	### `new MetaspacePreTokenizer(config)`

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Default</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td></td><td><p>The configuration object for the MetaspacePreTokenizer.</p>
	</td>
	</tr><tr>
	<td>config.replacement</td><td><code>string</code></td><td></td><td><p>The character to replace spaces with.</p>
	</td>
	</tr><tr>
	<td>[config.str_rep]</td><td><code>string</code></td><td><code>"config.replacement"</code></td><td><p>An optional string representation of the replacement character.</p>
	</td>
	</tr><tr>
	<td>[config.prepend_scheme]</td><td><code>'first'</code> \| <code>'never'</code> \| <code>'always'</code></td><td><code>'always'</code></td><td><p>The metaspace prepending scheme.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..MetaspacePreTokenizer+pre_tokenize_text" class="group"></a>

	### `metaspacePreTokenizer.pre_tokenize_text(text, [options])` ⇒ <code>Array.<string></code>

	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 [<code>MetaspacePreTokenizer</code>](#module_tokenizers..MetaspacePreTokenizer)
	Returns: <code>Array.<string></code> - A new list of pre-tokenized tokens.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The text to pre-tokenize.</p>
	</td>
	</tr><tr>
	<td>[options]</td><td><code>Object</code></td><td><p>The options for the pre-tokenization.</p>
	</td>
	</tr><tr>
	<td>[options.section_index]</td><td><code>number</code></td><td><p>The index of the section to pre-tokenize.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..MetaspaceDecoder" class="group"></a>

	## tokenizers~MetaspaceDecoder ⇐ <code>Decoder</code>

	MetaspaceDecoder class extends the Decoder class and decodes Metaspace tokenization.

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>Decoder</code>

	* [~MetaspaceDecoder](#module_tokenizers..MetaspaceDecoder) ⇐ <code>Decoder</code>
	* [`new MetaspaceDecoder(config)`](#new_module_tokenizers..MetaspaceDecoder_new)
	* [`.decode_chain()`](#module_tokenizers..MetaspaceDecoder+decode_chain) : <code>*</code>


	* * *

	<a id="new_module_tokenizers..MetaspaceDecoder_new" class="group"></a>

	### `new MetaspaceDecoder(config)`

	Constructs a new MetaspaceDecoder object.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration object for the MetaspaceDecoder.</p>
	</td>
	</tr><tr>
	<td>config.replacement</td><td><code>string</code></td><td><p>The string to replace spaces with.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..MetaspaceDecoder+decode_chain" class="group"></a>

	### `metaspaceDecoder.decode_chain()` : <code>*</code>

	Kind: instance method of [<code>MetaspaceDecoder</code>](#module_tokenizers..MetaspaceDecoder)

	* * *

	<a id="module_tokenizers..Precompiled" class="group"></a>

	## tokenizers~Precompiled ⇐ <code>Normalizer</code>

	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 [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>Normalizer</code>

	* [~Precompiled](#module_tokenizers..Precompiled) ⇐ <code>Normalizer</code>
	* [`new Precompiled(config)`](#new_module_tokenizers..Precompiled_new)
	* [`.normalize(text)`](#module_tokenizers..Precompiled+normalize) ⇒ <code>string</code>


	* * *

	<a id="new_module_tokenizers..Precompiled_new" class="group"></a>

	### `new Precompiled(config)`

	Create a new instance of Precompiled normalizer.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration object for the Precompiled normalizer.</p>
	</td>
	</tr><tr>
	<td>config.precompiled_charsmap</td><td><code>Object</code></td><td><p>The precompiled charsmap object.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..Precompiled+normalize" class="group"></a>

	### `precompiled.normalize(text)` ⇒ <code>string</code>

	Normalizes the given text by applying the precompiled charsmap.

	Kind: instance method of [<code>Precompiled</code>](#module_tokenizers..Precompiled)
	Returns: <code>string</code> - The normalized text.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The text to normalize.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..PreTokenizerSequence" class="group"></a>

	## tokenizers~PreTokenizerSequence ⇐ <code>PreTokenizer</code>

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

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>PreTokenizer</code>

	* [~PreTokenizerSequence](#module_tokenizers..PreTokenizerSequence) ⇐ <code>PreTokenizer</code>
	* [`new PreTokenizerSequence(config)`](#new_module_tokenizers..PreTokenizerSequence_new)
	* [`.pre_tokenize_text(text, [options])`](#module_tokenizers..PreTokenizerSequence+pre_tokenize_text) ⇒ <code>Array.<string></code>


	* * *

	<a id="new_module_tokenizers..PreTokenizerSequence_new" class="group"></a>

	### `new PreTokenizerSequence(config)`

	Creates an instance of PreTokenizerSequence.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration object for the pre-tokenizer sequence.</p>
	</td>
	</tr><tr>
	<td>config.pretokenizers</td><td><code>Array.<Object></code></td><td><p>An array of pre-tokenizer configurations.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..PreTokenizerSequence+pre_tokenize_text" class="group"></a>

	### `preTokenizerSequence.pre_tokenize_text(text, [options])` ⇒ <code>Array.<string></code>

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

	Kind: instance method of [<code>PreTokenizerSequence</code>](#module_tokenizers..PreTokenizerSequence)
	Returns: <code>Array.<string></code> - The pre-tokenized text.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The text to pre-tokenize.</p>
	</td>
	</tr><tr>
	<td>[options]</td><td><code>Object</code></td><td><p>Additional options for the pre-tokenization logic.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..WhitespacePreTokenizer" class="group"></a>

	## tokenizers~WhitespacePreTokenizer

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

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)

	* [~WhitespacePreTokenizer](#module_tokenizers..WhitespacePreTokenizer)
	* [`new WhitespacePreTokenizer(config)`](#new_module_tokenizers..WhitespacePreTokenizer_new)
	* [`.pre_tokenize_text(text, [options])`](#module_tokenizers..WhitespacePreTokenizer+pre_tokenize_text) ⇒ <code>Array.<string></code>


	* * *

	<a id="new_module_tokenizers..WhitespacePreTokenizer_new" class="group"></a>

	### `new WhitespacePreTokenizer(config)`

	Creates an instance of WhitespacePreTokenizer.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration object for the pre-tokenizer.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..WhitespacePreTokenizer+pre_tokenize_text" class="group"></a>

	### `whitespacePreTokenizer.pre_tokenize_text(text, [options])` ⇒ <code>Array.<string></code>

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

	Kind: instance method of [<code>WhitespacePreTokenizer</code>](#module_tokenizers..WhitespacePreTokenizer)
	Returns: <code>Array.<string></code> - An array of tokens produced by splitting the input text on whitespace.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The text to be pre-tokenized.</p>
	</td>
	</tr><tr>
	<td>[options]</td><td><code>Object</code></td><td><p>Additional options for the pre-tokenization logic.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..WhitespaceSplit" class="group"></a>

	## tokenizers~WhitespaceSplit ⇐ <code>PreTokenizer</code>

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

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)
	Extends: <code>PreTokenizer</code>

	* [~WhitespaceSplit](#module_tokenizers..WhitespaceSplit) ⇐ <code>PreTokenizer</code>
	* [`new WhitespaceSplit(config)`](#new_module_tokenizers..WhitespaceSplit_new)
	* [`.pre_tokenize_text(text, [options])`](#module_tokenizers..WhitespaceSplit+pre_tokenize_text) ⇒ <code>Array.<string></code>


	* * *

	<a id="new_module_tokenizers..WhitespaceSplit_new" class="group"></a>

	### `new WhitespaceSplit(config)`

	Creates an instance of WhitespaceSplit.

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration object for the pre-tokenizer.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..WhitespaceSplit+pre_tokenize_text" class="group"></a>

	### `whitespaceSplit.pre_tokenize_text(text, [options])` ⇒ <code>Array.<string></code>

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

	Kind: instance method of [<code>WhitespaceSplit</code>](#module_tokenizers..WhitespaceSplit)
	Returns: <code>Array.<string></code> - An array of tokens produced by splitting the input text on whitespace.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The text to be pre-tokenized.</p>
	</td>
	</tr><tr>
	<td>[options]</td><td><code>Object</code></td><td><p>Additional options for the pre-tokenization logic.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..ReplacePreTokenizer" class="group"></a>

	## tokenizers~ReplacePreTokenizer

	Kind: inner class of [<code>tokenizers</code>](#module_tokenizers)

	* [~ReplacePreTokenizer](#module_tokenizers..ReplacePreTokenizer)
	* [`new ReplacePreTokenizer(config)`](#new_module_tokenizers..ReplacePreTokenizer_new)
	* [`.pre_tokenize_text(text, [options])`](#module_tokenizers..ReplacePreTokenizer+pre_tokenize_text) ⇒ <code>Array.<string></code>


	* * *

	<a id="new_module_tokenizers..ReplacePreTokenizer_new" class="group"></a>

	### `new ReplacePreTokenizer(config)`

	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>config</td><td><code>Object</code></td><td><p>The configuration options for the pre-tokenizer.</p>
	</td>
	</tr><tr>
	<td>config.pattern</td><td><code>Object</code></td><td><p>The pattern used to split the text. Can be a string or a regex object.</p>
	</td>
	</tr><tr>
	<td>config.content</td><td><code>string</code></td><td><p>What to replace the pattern with.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..ReplacePreTokenizer+pre_tokenize_text" class="group"></a>

	### `replacePreTokenizer.pre_tokenize_text(text, [options])` ⇒ <code>Array.<string></code>

	Pre-tokenizes the input text by replacing certain characters.

	Kind: instance method of [<code>ReplacePreTokenizer</code>](#module_tokenizers..ReplacePreTokenizer)
	Returns: <code>Array.<string></code> - An array of tokens produced by replacing certain characters.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The text to be pre-tokenized.</p>
	</td>
	</tr><tr>
	<td>[options]</td><td><code>Object</code></td><td><p>Additional options for the pre-tokenization logic.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..BYTES_TO_UNICODE" class="group"></a>

	## `tokenizers~BYTES_TO_UNICODE` ⇒ <code>Object</code>

	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 [<code>tokenizers</code>](#module_tokenizers)
	Returns: <code>Object</code> - Object with utf-8 byte keys and unicode string values.

	* * *

	<a id="module_tokenizers..loadTokenizer" class="group"></a>

	## `tokenizers~loadTokenizer(pretrained_model_name_or_path, options)` ⇒ <code>Promise.<Array<any>></code>

	Loads a tokenizer from the specified path.

	Kind: inner method of [<code>tokenizers</code>](#module_tokenizers)
	Returns: <code>Promise.<Array<any>></code> - A promise that resolves with information about the loaded tokenizer.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>pretrained_model_name_or_path</td><td><code>string</code></td><td><p>The path to the tokenizer directory.</p>
	</td>
	</tr><tr>
	<td>options</td><td><code>PretrainedTokenizerOptions</code></td><td><p>Additional options for loading the tokenizer.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..regexSplit" class="group"></a>

	## `tokenizers~regexSplit(text, regex)` ⇒ <code>Array.<string></code>

	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 [<code>tokenizers</code>](#module_tokenizers)
	Returns: <code>Array.<string></code> - The split string.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The text to split.</p>
	</td>
	</tr><tr>
	<td>regex</td><td><code>RegExp</code></td><td><p>The regex to split on.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..createPattern" class="group"></a>

	## `tokenizers~createPattern(pattern, invert)` ⇒ <code>RegExp</code> \| <code>null</code>

	Helper method to construct a pattern from a config object.

	Kind: inner method of [<code>tokenizers</code>](#module_tokenizers)
	Returns: <code>RegExp</code> \| <code>null</code> - The compiled pattern.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Default</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>pattern</td><td><code>Object</code></td><td></td><td><p>The pattern object.</p>
	</td>
	</tr><tr>
	<td>invert</td><td><code>boolean</code></td><td><code>true</code></td><td><p>Whether to invert the pattern.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..objectToMap" class="group"></a>

	## `tokenizers~objectToMap(obj)` ⇒ <code>Map.<string, any></code>

	Helper function to convert an Object to a Map

	Kind: inner method of [<code>tokenizers</code>](#module_tokenizers)
	Returns: <code>Map.<string, any></code> - The map.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>obj</td><td><code>Object</code></td><td><p>The object to convert.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..prepareTensorForDecode" class="group"></a>

	## `tokenizers~prepareTensorForDecode(tensor)` ⇒ <code>Array.<number></code>

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

	Kind: inner method of [<code>tokenizers</code>](#module_tokenizers)
	Returns: <code>Array.<number></code> - The tensor as a list.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>tensor</td><td><code><a href="#Tensor">Tensor</a></code></td><td><p>The tensor to convert.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..clean_up_tokenization" class="group"></a>

	## `tokenizers~clean_up_tokenization(text)` ⇒ <code>string</code>

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

	Kind: inner method of [<code>tokenizers</code>](#module_tokenizers)
	Returns: <code>string</code> - The cleaned up text.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The text to clean up.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..remove_accents" class="group"></a>

	## `tokenizers~remove_accents(text)` ⇒ <code>string</code>

	Helper function to remove accents from a string.

	Kind: inner method of [<code>tokenizers</code>](#module_tokenizers)
	Returns: <code>string</code> - The text with accents removed.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The text to remove accents from.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..lowercase_and_remove_accent" class="group"></a>

	## `tokenizers~lowercase_and_remove_accent(text)` ⇒ <code>string</code>

	Helper function to lowercase a string and remove accents.

	Kind: inner method of [<code>tokenizers</code>](#module_tokenizers)
	Returns: <code>string</code> - The lowercased text with accents removed.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The text to lowercase and remove accents from.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..whitespace_split" class="group"></a>

	## `tokenizers~whitespace_split(text)` ⇒ <code>Array.<string></code>

	Split a string on whitespace.

	Kind: inner method of [<code>tokenizers</code>](#module_tokenizers)
	Returns: <code>Array.<string></code> - The split string.
	<table>
	<thead>
	<tr>
	<th>Param</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>text</td><td><code>string</code></td><td><p>The text to split.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..PretrainedTokenizerOptions" class="group"></a>

	## `tokenizers~PretrainedTokenizerOptions` : <code>Object</code>

	Additional tokenizer-specific properties.

	Kind: inner typedef of [<code>tokenizers</code>](#module_tokenizers)
	Properties

	<table>
	<thead>
	<tr>
	<th>Name</th><th>Type</th><th>Default</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>[legacy]</td><td><code>boolean</code></td><td><code>false</code></td><td><p>Whether or not the <code>legacy</code> behavior of the tokenizer should be used.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..BPENode" class="group"></a>

	## `tokenizers~BPENode` : <code>Object</code>

	Kind: inner typedef of [<code>tokenizers</code>](#module_tokenizers)
	Properties

	<table>
	<thead>
	<tr>
	<th>Name</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>token</td><td><code>string</code></td><td><p>The token associated with the node</p>
	</td>
	</tr><tr>
	<td>bias</td><td><code>number</code></td><td><p>A positional bias for the node.</p>
	</td>
	</tr><tr>
	<td>[score]</td><td><code>number</code></td><td><p>The score of the node.</p>
	</td>
	</tr><tr>
	<td>[prev]</td><td><code>BPENode</code></td><td><p>The previous node in the linked list.</p>
	</td>
	</tr><tr>
	<td>[next]</td><td><code>BPENode</code></td><td><p>The next node in the linked list.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..SplitDelimiterBehavior" class="group"></a>

	## `tokenizers~SplitDelimiterBehavior` : <code>'removed'</code> \| <code>'isolated'</code> \| <code>'mergedWithPrevious'</code> \| <code>'mergedWithNext'</code> \| <code>'contiguous'</code>

	Kind: inner typedef of [<code>tokenizers</code>](#module_tokenizers)

	* * *

	<a id="module_tokenizers..PostProcessedOutput" class="group"></a>

	## `tokenizers~PostProcessedOutput` : <code>Object</code>

	Kind: inner typedef of [<code>tokenizers</code>](#module_tokenizers)
	Properties

	<table>
	<thead>
	<tr>
	<th>Name</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>tokens</td><td><code>Array.<string></code></td><td><p>List of token produced by the post-processor.</p>
	</td>
	</tr><tr>
	<td>[token_type_ids]</td><td><code>Array.<number></code></td><td><p>List of token type ids produced by the post-processor.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..EncodingSingle" class="group"></a>

	## `tokenizers~EncodingSingle` : <code>Object</code>

	Kind: inner typedef of [<code>tokenizers</code>](#module_tokenizers)
	Properties

	<table>
	<thead>
	<tr>
	<th>Name</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>input_ids</td><td><code>Array.<number></code></td><td><p>List of token ids to be fed to a model.</p>
	</td>
	</tr><tr>
	<td>attention_mask</td><td><code>Array.<number></code></td><td><p>List of token type ids to be fed to a model</p>
	</td>
	</tr><tr>
	<td>[token_type_ids]</td><td><code>Array.<number></code></td><td><p>List of indices specifying which tokens should be attended to by the model</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..Message" class="group"></a>

	## `tokenizers~Message` : <code>Object</code>

	Kind: inner typedef of [<code>tokenizers</code>](#module_tokenizers)
	Properties

	<table>
	<thead>
	<tr>
	<th>Name</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>role</td><td><code>string</code></td><td><p>The role of the message (e.g., "user" or "assistant" or "system").</p>
	</td>
	</tr><tr>
	<td>content</td><td><code>string</code></td><td><p>The content of the message.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *

	<a id="module_tokenizers..BatchEncoding" class="group"></a>

	## `tokenizers~BatchEncoding` : <code>Array<number></code> \| <code>Array<Array<number>></code> \| [<code>Tensor</code>](#Tensor)

	Holds the output of the tokenizer's call function.

	Kind: inner typedef of [<code>tokenizers</code>](#module_tokenizers)
	Properties

	<table>
	<thead>
	<tr>
	<th>Name</th><th>Type</th><th>Description</th>
	</tr>
	</thead>
	<tbody>
	<tr>
	<td>input_ids</td><td><code>BatchEncodingItem</code></td><td><p>List of token ids to be fed to a model.</p>
	</td>
	</tr><tr>
	<td>attention_mask</td><td><code>BatchEncodingItem</code></td><td><p>List of indices specifying which tokens should be attended to by the model.</p>
	</td>
	</tr><tr>
	<td>[token_type_ids]</td><td><code>BatchEncodingItem</code></td><td><p>List of token type ids to be fed to a model.</p>
	</td>
	</tr> </tbody>
	</table>


	* * *



	<EditOnGithub source="https://github.com/huggingface/transformers.js/blob/main/docs/source/api/tokenizers.md" />

Xet Storage Details

Size:: 158 kB
Xet hash:: 80f5a122b29609a3c291da76e36601b332cec11f4f3f02d67361e128de11b756

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