Struct T5Model

Source
pub struct T5Model { /* private fields */ }
Expand description

§T5 Base model

Base architecture for T5 model. Usually complemented with a task-specific head, such as a language model head. It is made of the following blocks:

  • encoder: T5Stack (transformer) made of a vector of encoding layers
  • decoder: T5Stack (transformer) made of a vector of decoding layers with self attention and encoder cross-attention. caching is implemented for the decoder to avoid recalculating static states (encoder key/values and previously calculated decoder key/values)
  • embeddings: nn::Embedding Shared embeddings for the encoder and decoder.

Implementations§

Source§

impl T5Model

Source

pub fn new<'p, P>(p: P, config: &T5Config) -> T5Model
where P: Borrow<Path<'p>>,

Build a new T5Model

§Arguments
  • p - Variable store path for the root of the T5 model
  • config - T5Config object defining the model architecture
§Example
use rust_bert::t5::{T5Config, T5Model};
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 = T5Config::from_file(config_path);
let t5: T5Model = T5Model::new(&p.root() / "t5", &config);
Source

pub fn forward_t( &self, input_ids: Option<&Tensor>, attention_mask: Option<&Tensor>, encoder_outputs: Option<&Tensor>, decoder_input_ids: Option<&Tensor>, decoder_attention_mask: Option<&Tensor>, input_embeds: Option<&Tensor>, decoder_input_embeds: Option<&Tensor>, old_layer_states: Option<Vec<(Option<LayerState>, Option<LayerState>)>>, train: bool, ) -> T5ModelOutput

Forward pass through the model

§Arguments
  • input_ids - Optional input tensor of shape (batch size, source_sequence_length). This or input_embeds must be provided.
  • attention_mask - Optional attention mask of shape (batch size, source_sequence_length) for the encoder positions. Positions with a mask with value 0 will be masked.
  • decoder_input_ids - Optional input tensor of shape (batch size, target_sequence_length). This or decoder_input_embeds must be provided.
  • encoder_outputs - Optional tuple made of a tensor of shape (batch size, source_sequence_length, encoder_hidden_dim) and optional vectors of tensors of length num_encoder_layers with shape (batch size, source_sequence_length, hidden_size). These correspond to the encoder last hidden state and optional hidden states/attention weights for encoder layers. When provided, the encoder hidden state will not be recalculated. Useful for generation tasks.
  • decoder_attention_mask - Optional attention mask of shape (batch size, target_sequence_length) for the decoder positions. Positions with a mask with value 0 will be masked.
  • input_embeds - Optional input tensor of shape (batch size, source_sequence_length, embeddings dimension). This or input_ids must be provided.
  • decoder_input_embeds - Optional input tensor of shape (batch size, target_sequence_length, embeddings dimension). This or decoder_input_ids must be provided.
  • old_layer_states - Optional vector of length num_layers containing tuples of optional LayerStates containing the last calculated key and value pairs for the decoder. 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
  • T5ModelOutput containing:
    • decoder_output - Tensor of shape (batch size, target_sequence_length, hidden_size) representing the activations of the last decoder hidden state
    • encoder_hidden_states - Tensor of shape (batch size, source_sequence_length, hidden_size) representing the activations of the last encoder hidden state
    • cache - Option<Vec<(Option<Vec<LayerState, LayerState>>)>> of length n_layer containing the encoder padding mask and past keys and values for both the self attention and the encoder cross attention of each layer of the decoder.
    • all_encoder_hidden_states - Option<Vec<Tensor>> of length num_encoder_layers with shape (batch size, source_sequence_length, hidden_size)
    • all_encoder_attentions - Option<Vec<Tensor>> of length num_encoder_layers with shape (batch size, source_sequence_length, hidden_size)
    • all_decoder_hidden_states - Option<Vec<Tensor>> of length num_decoder_layers with shape (batch size, target_sequence_length, hidden_size)
    • all_decoder_attentions - Option<Vec<Tensor>> of length num_decoder_layers with shape (batch size, target_sequence_length, hidden_size)
§Example
use rust_bert::t5::{T5Config, T5Model};
let (batch_size, source_sequence_length, target_sequence_length) = (64, 128, 56);
let input_tensor = Tensor::rand(&[batch_size, source_sequence_length], (Int64, device));
let target_tensor = Tensor::rand(&[batch_size, target_sequence_length], (Int64, device));
let encoder_attention_mask =
    Tensor::ones(&[batch_size, source_sequence_length], (Int64, device));
let decoder_attention_mask =
    Tensor::ones(&[batch_size, source_sequence_length], (Int64, device));

let model_output = no_grad(|| {
    t5_model.forward_t(
        Some(&input_tensor),
        Some(&encoder_attention_mask),
        None,
        Some(&target_tensor),
        Some(&decoder_attention_mask),
        None,
        None,
        None,
        false,
    )
});

Auto Trait Implementations§

Blanket Implementations§

Source§

impl<T> Any for T
where T: 'static + ?Sized,

Source§

fn type_id(&self) -> TypeId

Gets the TypeId of self. Read more
Source§

impl<T> Borrow<T> for T
where T: ?Sized,

Source§

fn borrow(&self) -> &T

Immutably borrows from an owned value. Read more
Source§

impl<T> BorrowMut<T> for T
where T: ?Sized,

Source§

fn borrow_mut(&mut self) -> &mut T

Mutably borrows from an owned value. Read more
Source§

impl<T> From<T> for T

Source§

fn from(t: T) -> T

Returns the argument unchanged.

Source§

impl<T> Instrument for T

Source§

fn instrument(self, span: Span) -> Instrumented<Self>

Instruments this type with the provided Span, returning an Instrumented wrapper. Read more
Source§

fn in_current_span(self) -> Instrumented<Self>

Instruments this type with the current Span, returning an Instrumented wrapper. Read more
Source§

impl<T, U> Into<U> for T
where U: From<T>,

Source§

fn into(self) -> U

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

Source§

impl<T> IntoEither for T

Source§

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 more
Source§

fn into_either_with<F>(self, into_left: F) -> Either<Self, Self>
where F: FnOnce(&Self) -> bool,

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
Source§

impl<T> Pointable for T

Source§

const ALIGN: usize

The alignment of pointer.
Source§

type Init = T

The type for initializers.
Source§

unsafe fn init(init: <T as Pointable>::Init) -> usize

Initializes a with the given initializer. Read more
Source§

unsafe fn deref<'a>(ptr: usize) -> &'a T

Dereferences the given pointer. Read more
Source§

unsafe fn deref_mut<'a>(ptr: usize) -> &'a mut T

Mutably dereferences the given pointer. Read more
Source§

unsafe fn drop(ptr: usize)

Drops the object pointed to by the given pointer. Read more
Source§

impl<T> Same for T

Source§

type Output = T

Should always be Self
Source§

impl<T, U> TryFrom<U> for T
where U: Into<T>,

Source§

type Error = Infallible

The type returned in the event of a conversion error.
Source§

fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>

Performs the conversion.
Source§

impl<T, U> TryInto<U> for T
where U: TryFrom<T>,

Source§

type Error = <U as TryFrom<T>>::Error

The type returned in the event of a conversion error.
Source§

fn try_into(self) -> Result<U, <U as TryFrom<T>>::Error>

Performs the conversion.
Source§

impl<V, T> VZip<V> for T
where V: MultiLane<T>,

Source§

fn vzip(self) -> V

Source§

impl<T> WithSubscriber for T

Source§

fn with_subscriber<S>(self, subscriber: S) -> WithDispatch<Self>
where S: Into<Dispatch>,

Attaches the provided Subscriber to this type, returning a WithDispatch wrapper. Read more
Source§

fn with_current_subscriber(self) -> WithDispatch<Self>

Attaches the current default Subscriber to this type, returning a WithDispatch wrapper. Read more
Source§

impl<T> ErasedDestructor for T
where T: 'static,

Source§

impl<T> MaybeSendSync for T