pub struct XLNetForTokenClassification { /* private fields */ }
Expand description
§XLNetForTokenClassification
XLNet model with a classification head for token-level classification tasks It is made of the following blocks:
base_model
:XLNetModel
classifier
: Linear layer projecting the hidden layer output to the target space
Implementations§
Source§impl XLNetForTokenClassification
impl XLNetForTokenClassification
Sourcepub fn new<'p, P>(
p: P,
config: &XLNetConfig,
) -> Result<XLNetForTokenClassification, RustBertError>
pub fn new<'p, P>( p: P, config: &XLNetConfig, ) -> Result<XLNetForTokenClassification, RustBertError>
Build a new XLNetForTokenClassification
§Arguments
p
- Variable store path for the root of the XLNet modelconfig
-XLNetConfig
object defining the model architecture
§Example
use rust_bert::xlnet::{XLNetConfig, XLNetForTokenClassification};
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 = XLNetConfig::from_file(config_path);
let xlnet_model = XLNetForTokenClassification::new(&p.root(), &config).unwrap();
Sourcepub fn forward_t(
&self,
input_ids: Option<&Tensor>,
attention_mask: Option<&Tensor>,
old_layer_states: Option<Vec<Option<LayerState>>>,
perm_mask: Option<&Tensor>,
target_mapping: Option<&Tensor>,
token_type_ids: Option<&Tensor>,
input_embeds: Option<&Tensor>,
train: bool,
) -> XLNetTokenClassificationOutput
pub fn forward_t( &self, input_ids: Option<&Tensor>, attention_mask: Option<&Tensor>, old_layer_states: Option<Vec<Option<LayerState>>>, perm_mask: Option<&Tensor>, target_mapping: Option<&Tensor>, token_type_ids: Option<&Tensor>, input_embeds: Option<&Tensor>, train: bool, ) -> XLNetTokenClassificationOutput
Forward pass through the model
§Arguments
input_ids
- Optional input tensor of shape (batch size, sequence_length). This orinput_embeds
must be provided.attention_mask
- Optional attention mask of shape (batch size, sequence_length) for the encoder positions. Positions with a mask with value 0 will be masked.perm_mask
- Optional tensor of shape (batch size, sequence_length, sequence_length). Mask to indicate the attention pattern for each input token (only used for pre-training over permutations, rather than simple token masking).target_mapping
- Optional tensor of shape (batch size, num_tokens, sequence_length) indicating the position of the masked words to predict.token_type_ids
- Optional tensor (batch size, sequence_length) indicating the sentence ID of the token (0: first sentence, 1: second sentence).input_embeds
- Optional input tensor of shape (batch size, sequence_length, embeddings dimension). This orinput_ids
must be provided.old_layer_states
- Optional vector of lengthnum_layers
containing optionalLayerStates
containing the last calculated content for the attention layers. This avoids recomputing attention weights at past positions and speeds up decoding.train
- boolean flag to turn on/off the dropout layers in the model. Should be set to false for inference.
§Returns
XLNetTokenClassificationOutput
containing:logits
-Tensor
of shape (batch size, sequence_length, num_classes) representing the logits for each batch item, token position and classnext_cache
-Option<Vec<Option<LayerState>>>
of length n_layer containing the past content for the the attention layers with shape (past_sequence_length, batch size, hidden_size)all_hidden_states
-Option<Vec<(Tensor, Option<Tensor>)>>
of length n_layer with shape (batch size, sequence_length, hidden_size) (with optional query stream states if used)all_attentions
-Option<Vec<(Tensor, Option<Tensor>)>>
of length n_layer with shape (batch size, sequence_length, hidden_size) (with optional query stream states if used)
§Example
use rust_bert::xlnet::{XLNetConfig, XLNetForTokenClassification};
let (batch_size, sequence_length) = (64, 128);
let input_tensor = Tensor::rand(&[batch_size, sequence_length], (Int64, device));
let attention_mask = Tensor::ones(&[batch_size, sequence_length], (Int64, device));
let target_tensor = Tensor::ones(&[batch_size, sequence_length], (Int64, device));
let target_mapping = Tensor::zeros(&[64, 1, 128], (Kind::Float, device));
let _ = target_mapping.narrow(2, 3, 1).fill_(1.0);
let model_output = no_grad(|| {
xlnet_model.forward_t(
Some(&input_tensor),
Some(&attention_mask),
None,
Some(&target_mapping),
None,
None,
None,
false
)
});
Auto Trait Implementations§
impl Freeze for XLNetForTokenClassification
impl RefUnwindSafe for XLNetForTokenClassification
impl Send for XLNetForTokenClassification
impl !Sync for XLNetForTokenClassification
impl Unpin for XLNetForTokenClassification
impl UnwindSafe for XLNetForTokenClassification
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