pub struct RobertaForTokenClassification { /* private fields */ }
Expand description
§RoBERTa for token classification (e.g. NER, POS)
Token-level classifier predicting a label for each token provided. Note that because of bpe tokenization, the labels predicted are not necessarily aligned with words in the sentence. It is made of the following blocks:
roberta
: Base RoBERTa modelclassifier
: Linear layer for token classification
Implementations§
Source§impl RobertaForTokenClassification
impl RobertaForTokenClassification
Sourcepub fn new<'p, P>(
p: P,
config: &BertConfig,
) -> Result<RobertaForTokenClassification, RustBertError>
pub fn new<'p, P>( p: P, config: &BertConfig, ) -> Result<RobertaForTokenClassification, RustBertError>
Build a new RobertaForTokenClassification
§Arguments
p
- Variable store path for the root of the RobertaForMaskedLM modelconfig
-RobertaConfig
object defining the model architecture and vocab size
§Example
use rust_bert::roberta::{RobertaConfig, RobertaForMultipleChoice};
use rust_bert::Config;
use std::path::Path;
use tch::{nn, Device};
let config_path = Path::new("path/to/config.json");
let device = Device::Cpu;
let p = nn::VarStore::new(device);
let config = RobertaConfig::from_file(config_path);
let roberta = RobertaForMultipleChoice::new(&p.root() / "roberta", &config);
Sourcepub fn forward_t(
&self,
input_ids: Option<&Tensor>,
mask: Option<&Tensor>,
token_type_ids: Option<&Tensor>,
position_ids: Option<&Tensor>,
input_embeds: Option<&Tensor>,
train: bool,
) -> RobertaTokenClassificationOutput
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>, train: bool, ) -> RobertaTokenClassificationOutput
Forward pass through the model
§Arguments
input_ids
- Optional input tensor of shape (batch size, sequence_length). If None, pre-computed embeddings must be provided (seeinput_embeds
)mask
- Optional mask of shape (batch size, sequence_length). Masked position have value 0, non-masked value 1. If None set to 1token_type_ids
-Optional segment id of shape (batch size, sequence_length). Convention is value of 0 for the first sentence (incl. ) and 1 for the second sentence. If None set to 0.position_ids
- Optional position ids of shape (batch size, sequence_length). If None, will be incremented from 0.input_embeds
- Optional pre-computed input embeddings of shape (batch size, sequence_length, hidden_size). If None, input ids must be provided (seeinput_ids
)train
- boolean flag to turn on/off the dropout layers in the model. Should be set to false for inference.
§Returns
RobertaTokenClassificationOutput
containing:logits
-Tensor
of shape (batch size, sequence_length, num_labels) containing the logits for each of the input tokens and classesall_hidden_states
-Option<Vec<Tensor>>
of length num_hidden_layers with shape (batch size, sequence_length, hidden_size)all_attentions
-Option<Vec<Tensor>>
of length num_hidden_layers with shape (batch size, sequence_length, hidden_size)
§Example
use rust_bert::roberta::RobertaForTokenClassification;
let (batch_size, sequence_length) = (64, 128);
let input_tensor = Tensor::rand(&[batch_size, sequence_length], (Int64, device));
let mask = Tensor::zeros(&[batch_size, sequence_length], (Int64, device));
let token_type_ids = Tensor::zeros(&[batch_size, sequence_length], (Int64, device));
let position_ids = Tensor::arange(sequence_length, (Int64, device))
.expand(&[batch_size, sequence_length], true);
let model_output = no_grad(|| {
roberta_model.forward_t(
Some(&input_tensor),
Some(&mask),
Some(&token_type_ids),
Some(&position_ids),
None,
false,
)
});
Auto Trait Implementations§
impl Freeze for RobertaForTokenClassification
impl RefUnwindSafe for RobertaForTokenClassification
impl Send for RobertaForTokenClassification
impl !Sync for RobertaForTokenClassification
impl Unpin for RobertaForTokenClassification
impl UnwindSafe for RobertaForTokenClassification
Blanket Implementations§
Source§impl<T> BorrowMut<T> for Twhere
T: ?Sized,
impl<T> BorrowMut<T> for Twhere
T: ?Sized,
Source§fn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more
Source§impl<T> Instrument for T
impl<T> Instrument for T
Source§fn instrument(self, span: Span) -> Instrumented<Self>
fn instrument(self, span: Span) -> Instrumented<Self>
Source§fn in_current_span(self) -> Instrumented<Self>
fn in_current_span(self) -> Instrumented<Self>
Source§impl<T> IntoEither for T
impl<T> IntoEither for T
Source§fn into_either(self, into_left: bool) -> Either<Self, Self>
fn into_either(self, into_left: bool) -> Either<Self, Self>
Converts
self
into a Left
variant of Either<Self, Self>
if into_left
is true
.
Converts self
into a Right
variant of Either<Self, Self>
otherwise. Read moreSource§fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
Converts
self
into a Left
variant of Either<Self, Self>
if into_left(&self)
returns true
.
Converts self
into a Right
variant of Either<Self, Self>
otherwise. Read more