Struct tokenizers::decoders::wordpiece::WordPiece

#[non_exhaustive]
pub struct WordPiece {
    pub prefix: String,
    pub cleanup: bool,
}

The WordPiece decoder takes care of decoding a list of wordpiece tokens back into a readable string.

Fields (Non-exhaustive)

Non-exhaustive structs could have additional fields added in future. Therefore, non-exhaustive structs cannot be constructed in external crates using the traditional Struct { .. } syntax; cannot be matched against without a wildcard ..; and struct update syntax will not work.

prefix: String

The prefix to be used for continuing subwords

cleanup: bool

Whether to cleanup some tokenization artifacts (spaces before punctuation, …)

Implementations

impl WordPiece

pub fn new(prefix: String, cleanup: bool) -> Self

Trait Implementations

impl Clone for WordPiece

fn clone(&self) -> WordPiece

Returns a copy of the value.

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

Performs copy-assignment from source.

impl Debug for WordPiece

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

Formats the value using the given formatter.

impl Decoder for WordPiece

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

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

impl Default for WordPiece

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for WordPiece

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl From<WordPiece> for DecoderWrapper

fn from(from: WordPiece) -> Self

Converts to this type from the input type.

impl Serialize for WordPiece

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.