Struct rust_bert::distilbert::DistilBertModelClassifier

pub struct DistilBertModelClassifier { /* fields omitted */ }

DistilBERT for sequence classification

Base DistilBERT model with a pre-classifier and classifier heads to perform sentence or document-level classification It is made of the following blocks:

• distil_bert_model: Base DistilBertModel
• pre_classifier: DistilBERT linear layer for classification
• classifier: DistilBERT linear layer for classification

Implementations

impl DistilBertModelClassifier

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

Build a new DistilBertModelClassifier for sequence classification

Arguments

• p - Variable store path for the root of the DistilBertModelClassifier model
• config - DistilBertConfig object defining the model architecture

Example

use rust_bert::distilbert::{DistilBertConfig, DistilBertModelClassifier};
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 = DistilBertConfig::from_file(config_path);
let distil_bert: DistilBertModelClassifier =
    DistilBertModelClassifier::new(&p.root() / "distilbert", &config);

pub fn forward_t(
    &self,
    input: Option<&Tensor>,
    mask: Option<&Tensor>,
    input_embeds: Option<&Tensor>,
    train: bool
) -> Result<DistilBertSequenceClassificationOutput, RustBertError>

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
• 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)
• train - boolean flag to turn on/off the dropout layers in the model. Should be set to false for inference.

Returns

• DistilBertSequenceClassificationOutput containing:
  • logits - Tensor of shape (batch size, num_labels)
  • 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

use rust_bert::distilbert::{DistilBertConfig, DistilBertModelClassifier};
 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 model_output = no_grad(|| {
   distilbert_model
        .forward_t(Some(&input_tensor),
                   Some(&mask),
                   None,
                   false).unwrap()
   });