Struct rust_tokenizers::vocab::Gpt2Vocab

pub struct Gpt2Vocab {
    pub values: HashMap<String, i64>,
    pub indices: HashMap<i64, String>,
    pub unknown_value: &'static str,
    pub special_values: HashMap<String, i64>,
    pub special_indices: HashMap<i64, String>,
}

GPT2 Vocab

Vocabulary for GPT2 tokenizer. Contains the following special values:

• BOS token
• EOS token

Expects a JSON-format vocabulary when created from file.

Fields

values: HashMap<String, i64>

A mapping of tokens as string to indices (i.e. the encoder base)

indices: HashMap<i64, String>

A mapping of token ids to strings (i.e. the decoder base)

unknown_value: &'static str

The string to use for unknown (out of vocabulary) tokens

special_values: HashMap<String, i64>

A mapping of special value tokens as strings to IDs (i.e. the encoder base for special values), special values typically include things like BOS/EOS markers, class markers, mask markers and padding markers

special_indices: HashMap<i64, String>

A mapping of special value tokens as IDs to strings (i.e. the decoder base for special values)

Implementations

impl Gpt2Vocab

pub fn bos_value() -> &'static str

Returns the BOS token for GPT2 (<|endoftext|>)

pub fn eos_value() -> &'static str

Returns the EOS token for GPT2 (<|endoftext|>)

Trait Implementations

impl Clone for Gpt2Vocab

fn clone(&self) -> Gpt2Vocab

Returns a copy of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for Gpt2Vocab

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl MultiThreadedTokenizer<Gpt2Vocab> for Gpt2Tokenizer

fn vocab(&self) -> &T

returns a reference to the tokenizer vocabulary

fn tokenize_list_with_offsets<S, ST>(
    &self,
    text_list: S
) -> Vec<TokensWithOffsets> where
    S: AsRef<[ST]>,
    ST: AsRef<str> + Sync, 

Tokenize a list of strings (with multithreading), where each corresponds to for example a sentence, returns a vector of TokensWithOffsets containing the tokens and their offset information. This calls tokenize_with_offsets on the list provided.

fn tokenize_list<S, ST>(&self, text_list: S) -> Vec<Vec<String>> where
    S: AsRef<[ST]>,
    ST: AsRef<str> + Sync, 

Multithreaded tokenization of a list of strings, returning tokens with offset information

fn encode_list<S, ST>(
    &self,
    text_list: S,
    max_len: usize,
    truncation_strategy: &TruncationStrategy,
    stride: usize
) -> Vec<TokenizedInput> where
    S: AsRef<[ST]>,
    ST: AsRef<str> + Sync, 

Multithreaded encoding of a sequence of string-like texts (tokenization followed by encoding). Not that in contrast with encode optional second text, each text provided is encoded independently.

fn encode_pair_list<S, ST>(
    &self,
    text_list: S,
    max_len: usize,
    truncation_strategy: &TruncationStrategy,
    stride: usize
) -> Vec<TokenizedInput> where
    S: AsRef<[(ST, ST)]>,
    ST: AsRef<str> + Sync, 

Multithreaded ncoding of a sequence of string-like text pairs (tokenization followed by encoding). This combines with encode with the list processing of encode_list.

fn decode_list(
    &self,
    token_ids_list: Vec<Vec<i64>>,
    skip_special_tokens: bool,
    clean_up_tokenization_spaces: bool
) -> Vec<String>

Multithreaded conversion a list of sequence of ids (integer) into a string, using the tokenizer and vocabulary with options to remove special tokens and clean up tokenization spaces. This calls decode for each provided sequence of ids

impl Tokenizer<Gpt2Vocab> for Gpt2Tokenizer

fn vocab(&self) -> &Gpt2Vocab

returns a reference to the tokenizer vocabulary

fn tokenize_to_tokens(&self, initial_token: TokenRef<'_>) -> Vec<Token>

Tokenize a TokenRef, returning a sequence of tokens

fn convert_tokens_to_string(&self, tokens: Vec<String>) -> String

Converts a sequence of strings into a single string. This will clean-up artifacts from tokenization (for example sub ##word) and generate a single output string

fn tokenize<S: AsRef<str>>(&self, text: S) -> Vec<String>

Tokenize a string, returns a vector of tokens as strings. Use tokenize_with_offsets or tokenize_to_tokens to return offset information.

fn tokenize_with_offsets<S: AsRef<str>>(&self, text: S) -> TokensWithOffsets

Tokenize a string, returning tokens with offset information

fn tokenize_list<S, ST>(&self, text_list: S) -> Vec<Vec<String>> where
    S: AsRef<[ST]>,
    ST: AsRef<str>, 

Tokenize a list of strings, returning tokens with offset information

fn tokenize_list_with_offsets<S, ST>(
    &self,
    text_list: S
) -> Vec<TokensWithOffsets> where
    S: AsRef<[ST]>,
    ST: AsRef<str>, 

Tokenize a list of strings, where each corresponds to for example a sentence, returns a vector of TokensWithOffsets containing the tokens and their offset information. This calls tokenize_with_offsets on the list provided.

fn convert_tokens_to_ids<S, ST>(&self, tokens: S) -> Vec<i64> where
    S: AsRef<[ST]>,
    ST: AsRef<str>, 

Convert a slice of string-like to a vector ot token indices

fn encode<S: AsRef<str>>(
    &self,
    text_1: S,
    text_2: Option<S>,
    max_len: usize,
    truncation_strategy: &TruncationStrategy,
    stride: usize
) -> TokenizedInput

Encode a string-like (tokenization followed by encoding)

fn encode_list<S, ST>(
    &self,
    text_list: S,
    max_len: usize,
    truncation_strategy: &TruncationStrategy,
    stride: usize
) -> Vec<TokenizedInput> where
    S: AsRef<[ST]>,
    ST: AsRef<str>, 

Encode a sequence of string-like texts (tokenization followed by encoding). Not that in contrast with encode optional second text, each text provided is encoded independently.

fn encode_pair_list<S, ST>(
    &self,
    text_list: S,
    max_len: usize,
    truncation_strategy: &TruncationStrategy,
    stride: usize
) -> Vec<TokenizedInput> where
    S: AsRef<[(ST, ST)]>,
    ST: AsRef<str>, 

Encode a sequence of string-like text pairs (tokenization followed by encoding). This combines with encode with the list processing of encode_list.

fn decode_to_vec(
    &self,
    token_ids: Vec<i64>,
    skip_special_tokens: bool
) -> Vec<String>

Decode a sequence of token indices to a sequence of Strings, optionally skipping special indices

fn decode(
    &self,
    token_ids: Vec<i64>,
    skip_special_tokens: bool,
    clean_up_tokenization_spaces: bool
) -> String

Converts a sequence of ids (integer) into a string, using the tokenizer and vocabulary with options to remove special tokens and clean up tokenization spaces.

fn clean_up_tokenization(&self, input_string: String) -> String

Cleans-up tokenization artifacts (for example whitespace before punctuation)

fn decode_list(
    &self,
    token_ids_list: Vec<Vec<i64>>,
    skip_special_tokens: bool,
    clean_up_tokenization_spaces: bool
) -> Vec<String>

Converts a list of sequence of ids (integer) into a string, using the tokenizer and vocabulary with options to remove special tokens and clean up tokenization spaces. This calls decode for each provided sequence of ids

fn build_input_with_special_tokens(
    &self,
    tokens_ids_with_offsets_1: TokenIdsWithOffsets,
    tokens_ids_with_offsets_2: Option<TokenIdsWithOffsets>
) -> TokenIdsWithSpecialTokens

Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens.

impl Vocab for Gpt2Vocab

fn unknown_value() -> &'static str

Associative function returning the unknown value for the vocabulary

fn get_unknown_value(&self) -> &'static str

Returns the unknown value on an instance

fn values(&self) -> &HashMap<String, i64>

Return the map of token strings to IDs

fn indices(&self) -> &HashMap<i64, String>

Return the map of token IDs to strings

fn special_values(&self) -> &HashMap<String, i64>

Return the map of token strings to IDs

fn special_indices(&self) -> &HashMap<i64, String>

Return the map of token IDs to strings for special values

fn from_file(path: &str) -> Result<Gpt2Vocab, TokenizerError>

Read a vocabulary from file

fn token_to_id(&self, token: &str) -> i64

Converts a token to an id.

fn id_to_token(&self, id: &i64) -> String

Converts an id to a token.

fn read_vocab_file(path: &str) -> Result<HashMap<String, i64>, TokenizerError>

Read a Bert-style vocab.txt file (single column, one token per line) The from_file method should be preferred, and needs to be implemented by the specific vocabularies

fn _token_to_id(
    &self,
    token: &str,
    values: &HashMap<String, i64>,
    special_values: &HashMap<String, i64>,
    unknown_value: &str
) -> i64

Converts a token to an id, provided a HashMap of values, a HashMap of special values and the unknown value token string representation. This is not meant to be directly used, the method token_to_id offers a more convenient interface for most vocabularies, but needs to be implemented by the specific vocabulary.

fn _id_to_token(
    &self,
    id: &i64,
    indices: &HashMap<i64, String>,
    special_indices: &HashMap<i64, String>,
    unknown_value: &str
) -> String

Converts an id to a token, provided a HashMap of values, a HashMap of special values and the unknown value token string representation. This is not meant to be directly used, the method id_to_token offers a more convenient interface for most vocabularies, but needs to be implemented by the specific vocabulary.

fn _register_as_special_value(
    token: &str,
    values: &HashMap<String, i64>,
    special_values: &mut HashMap<String, i64>
) -> Result<(), TokenizerError>

Register a token as a special value

fn convert_tokens_to_ids(&self, tokens: &[&str]) -> Vec<i64>

Converts a list of tokens to a list of indices.