[−][src]Struct rust_bert::bert::BertModel
BERT Base model
Base architecture for BERT models. Task-specific models will be built from this common base model It is made of the following blocks:
embeddings
:token
,position
andsegment_id
embeddingsencoder
: Encoder (transformer) made of a vector of layers. Each layer is made of a self-attention layer, an intermediate (linear) and output (linear + layer norm) layerspooler
: linear layer applied to the first element of the sequence ([MASK] token)is_decoder
: Flag indicating if the model is used as a decoder. If set to true, a causal mask will be applied to hide future positions that should not be attended to.
Methods
impl<T: BertEmbedding> BertModel<T>
[src]
Defines the implementation of the BertModel. The BERT model shares many similarities with RoBERTa, main difference being the embeddings.
Therefore the forward pass of the model is shared and the type of embedding used is abstracted away. This allows to create
BertModel<RobertaEmbeddings>
or BertModel<BertEmbeddings>
for each model type.
pub fn new(p: &Path, config: &BertConfig) -> BertModel<T>
[src]
Build a new BertModel
Arguments
p
- Variable store path for the root of the BERT modelconfig
-BertConfig
object defining the model architecture and decoder status
Example
use rust_bert::bert::{BertModel, BertConfig, BertEmbeddings}; use tch::{nn, Device}; use rust_bert::Config; use std::path::Path; let config_path = Path::new("path/to/config.json"); let device = Device::Cpu; let p = nn::VarStore::new(device); let config = BertConfig::from_file(config_path); let bert: BertModel<BertEmbeddings> = BertModel::new(&(&p.root() / "bert"), &config);
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
) -> Result<(Tensor, Tensor, Option<Vec<Tensor>>, Option<Vec<Tensor>>), &'static str>
[src]
&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
) -> Result<(Tensor, Tensor, Option<Vec<Tensor>>, Option<Vec<Tensor>>), &'static str>
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. [SEP]) 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
)encoder_hidden_states
- Optional encoder hidden state of shape (batch size, encoder_sequence_length, hidden_size). If the model is defined as a decoder and theencoder_hidden_states
is not None, used in the cross-attention layer as keys and values (query from the decoder).encoder_mask
- Optional encoder attention mask of shape (batch size, encoder_sequence_length). If the model is defined as a decoder and theencoder_hidden_states
is not None, used to mask encoder values. Positions with value 0 will be masked.train
- boolean flag to turn on/off the dropout layers in the model. Should be set to false for inference.
Returns
output
-Tensor
of shape (batch size, sequence_length, hidden_size)pooled_output
-Tensor
of shape (batch size, hidden_size)hidden_states
-Option<Vec<Tensor>>
of length num_hidden_layers with shape (batch size, sequence_length, hidden_size)attentions
-Option<Vec<Tensor>>
of length num_hidden_layers with shape (batch size, sequence_length, hidden_size)
Example
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 (output, pooled_output, all_hidden_states, all_attentions) = no_grad(|| { bert_model .forward_t(Some(input_tensor), Some(mask), Some(token_type_ids), Some(position_ids), None, &None, &None, false).unwrap() });
Auto Trait Implementations
impl<T> !RefUnwindSafe for BertModel<T>
impl<T> !Send for BertModel<T>
impl<T> !Sync for BertModel<T>
impl<T> Unpin for BertModel<T> where
T: Unpin,
T: Unpin,
impl<T> !UnwindSafe for BertModel<T>
Blanket Implementations
impl<T> Any for T where
T: 'static + ?Sized,
[src]
T: 'static + ?Sized,
impl<T> Borrow<T> for T where
T: ?Sized,
[src]
T: ?Sized,
impl<T> BorrowMut<T> for T where
T: ?Sized,
[src]
T: ?Sized,
fn borrow_mut(&mut self) -> &mut T
[src]
impl<T> From<T> for T
[src]
impl<T, U> Into<U> for T where
U: From<T>,
[src]
U: From<T>,
impl<T, U> TryFrom<U> for T where
U: Into<T>,
[src]
U: Into<T>,
type Error = Infallible
The type returned in the event of a conversion error.
fn try_from(value: U) -> Result<T, <T as TryFrom<U>>::Error>
[src]
impl<T, U> TryInto<U> for T where
U: TryFrom<T>,
[src]
U: TryFrom<T>,