pub struct ReformerModel { /* private fields */ }
Expand description
§Reformer Base model
Base architecture for the Reformer model. Usually complemented with a task-specific head, such as a language model head. It is made of the following blocks:
embeddings
:ReformerEmbeddings
Reformer embeddings, combining word and position embeddingsencoder
:ReformerEncoder
(transformer) made of a vector of Reformer layer with local or LSH attention. caching is implemented for the decoder to avoid recalculating static states (encoder key/values and previously calculated decoder key/values)least_common_mult_chunk_length
: least common chunk length for all attention layersmin_chunk_length
: minimum chunk length for all attention layerspad_token_id
: padding token id used to pad to chunk length multiple if input is long enough to be chunked.
Implementations§
Source§impl ReformerModel
impl ReformerModel
Sourcepub fn new<'p, P>(
p: P,
config: &ReformerConfig,
) -> Result<ReformerModel, RustBertError>
pub fn new<'p, P>( p: P, config: &ReformerConfig, ) -> Result<ReformerModel, RustBertError>
Build a new ReformerModel
§Arguments
p
- Variable store path for the root of the BART modelconfig
-ReformerConfig
object defining the model architecture
§Example
use rust_bert::reformer::{ReformerConfig, ReformerModel};
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 = ReformerConfig::from_file(config_path);
let reformer_model: ReformerModel =
ReformerModel::new(&p.root() / "reformer", &config).unwrap();
Sourcepub fn forward_t(
&self,
input_ids: Option<&Tensor>,
position_ids: Option<&Tensor>,
input_embeds: Option<&Tensor>,
attention_mask: Option<&Tensor>,
num_hashes: Option<i64>,
old_layer_states: Option<Vec<Option<LayerState>>>,
train: bool,
) -> Result<ReformerModelOutput, RustBertError>
pub fn forward_t( &self, input_ids: Option<&Tensor>, position_ids: Option<&Tensor>, input_embeds: Option<&Tensor>, attention_mask: Option<&Tensor>, num_hashes: Option<i64>, old_layer_states: Option<Vec<Option<LayerState>>>, train: bool, ) -> Result<ReformerModelOutput, RustBertError>
Forward pass through the model
§Arguments
input_ids
- Optional input tensor of shape (batch size, sequence_length). Must be provided when no pre-computed embeddings are given.position_ids
- Optional input tensor of shape (batch size, sequence_length). If not provided will be calculated on the fly starting from position 0.input_embeds
- Optional input tensor of shape (batch size, sequence_length, embeddings_dim). Must be provided when no input ids are given.attention_mask
- Optional attention mask of shape (batch size, sequence_length). Positions with a mask with value 0 will be masked.num_hashes
- Optional specification of the number of hashes to use. If not provided will use the value provided in the model configuration.old_layer_states
- Optional cached input (Option<Vec<Option<LayerState>>>
) containing previous values for the cached states and buckets.train
- boolean flag to turn on/off the dropout layers in the model. Should be set to false for inference.
§Returns
ReformerModelOutput
containing:hidden_states
-Tensor
of shape (batch size, sequence_length, hidden_size) representing the activations of the last hidden stateall_hidden_states
-Option<Vec<Tensor>>
of length n_layers with shape (batch size, sequence_length, hidden_size)all_attentions
-Option<Vec<Tensor>>
of length n_layers with shape (batch size, sequence_length, hidden_size)cache
-Option<Vec<Option<LayerState>>>
of length n_layer containing values for the states and buckets for future use.
§Example
use rust_bert::reformer::{ReformerConfig, ReformerModel};
let (batch_size, sequence_length) = (64, 128);
let input_tensor = Tensor::rand(&[batch_size, sequence_length], (Int64, device));
let input_positions = Tensor::arange(sequence_length, (Kind::Int64, device))
.unsqueeze(0)
.expand(&[batch_size, sequence_length], true);
let attention_mask = Tensor::ones(&[batch_size, sequence_length], (Int64, device));
let model_output = no_grad(|| {
reformer_model.forward_t(
Some(&input_tensor),
Some(&input_positions),
None,
Some(&attention_mask),
Some(4),
None,
false,
)
});
Auto Trait Implementations§
impl Freeze for ReformerModel
impl RefUnwindSafe for ReformerModel
impl Send for ReformerModel
impl !Sync for ReformerModel
impl Unpin for ReformerModel
impl UnwindSafe for ReformerModel
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