Enum rust_bert::pipelines::masked_language::MaskedLanguageOption

pub enum MaskedLanguageOption {
    Bert(BertForMaskedLM),
    Deberta(DebertaForMaskedLM),
    DebertaV2(DebertaV2ForMaskedLM),
    Roberta(RobertaForMaskedLM),
    XLMRoberta(RobertaForMaskedLM),
    FNet(FNetForMaskedLM),
}

Abstraction that holds one particular masked language model, for any of the supported models

Variants

Bert(BertForMaskedLM)

Bert for Masked Language

Deberta(DebertaForMaskedLM)

DeBERTa for Masked Language

DebertaV2(DebertaV2ForMaskedLM)

DeBERTa V2 for Masked Language

Roberta(RobertaForMaskedLM)

Roberta for Masked Language

XLMRoberta(RobertaForMaskedLM)

XLMRoberta for Masked Language

FNet(FNetForMaskedLM)

FNet for Masked Language

Implementations

impl MaskedLanguageOption

pub fn new<'p, P>(
    model_type: ModelType,
    p: P,
    config: &ConfigOption
) -> Result<Self, RustBertError>where
    P: Borrow<Path<'p>>,

Instantiate a new masked language model of the supplied type.

Arguments

• model_type - ModelType indicating the model type to load (must match with the actual data to be loaded)
• p - tch::nn::Path path to the model file to load (e.g. model.ot)
• config - A configuration (the model type of the configuration must be compatible with the value for model_type)

pub fn model_type(&self) -> ModelType

Returns the ModelType for this MaskedLanguageOption

pub fn forward_t(
    &self,
    input_ids: Option<&Tensor>,
    mask: Option<&Tensor>,
    token_type_ids: Option<&Tensor>,
    position_ids: Option<&Tensor>,
    input_embeds: Option<&Tensor>,
    encoder_hidden_states: Option<&Tensor>,
    encoder_mask: Option<&Tensor>,
    train: bool
) -> Tensor

Interface method to forward_t() of the particular models.