Struct rust_bert::bert::BertForMaskedLM

pub struct BertForMaskedLM { /* fields omitted */ }

BERT for masked language model

Base BERT model with a masked language model head to predict missing tokens, for example "Looks like one [MASK] is missing" -> "person" It is made of the following blocks:

• bert: Base BertModel
• cls: BERT LM prediction head

Implementations

impl BertForMaskedLM

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

Build a new BertForMaskedLM

Arguments

• p - Variable store path for the root of the BertForMaskedLM model
• config - BertConfig object defining the model architecture and vocab size

Example

use rust_bert::bert::{BertConfig, BertForMaskedLM};
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 = BertConfig::from_file(config_path);
let bert = BertForMaskedLM::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
) -> BertMaskedLMOutput

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 (see input_embeds)
• mask - Optional mask of shape (batch size, sequence_length). Masked position have value 0, non-masked value 1. If None set to 1
• token_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 (see input_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 the encoder_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 the encoder_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

• BertMaskedLMOutput containing:
  • prediction_scores - Tensor of shape (batch size, sequence_length, vocab_size)
  • all_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

let (batch_size, sequence_length) = (64, 128);
let input_tensor = Tensor::rand(&[batch_size, sequence_length], (Kind::Int64, device));
let mask = Tensor::zeros(&[batch_size, sequence_length], (Kind::Int64, device));
let token_type_ids = Tensor::zeros(&[batch_size, sequence_length], (Kind::Int64, device));
let position_ids = Tensor::arange(sequence_length, (Kind::Int64, device))
    .expand(&[batch_size, sequence_length], true);

let model_output = no_grad(|| {
    bert_model.forward_t(
        Some(&input_tensor),
        Some(&mask),
        Some(&token_type_ids),
        Some(&position_ids),
        None,
        None,
        None,
        false,
    )
});