Struct DistilBertModel

pub struct DistilBertModel { /* private fields */ }

DistilBERT Base model

Base architecture for DistilBERT models. Task-specific models will be built from this common base model It is made of the following blocks:

• embeddings: token, position embeddings
• transformer: Transformer made of a vector of layers. Each layer is made of a multi-head self-attention layer, layer norm and linear layers.

Implementations

impl DistilBertModel

Defines the implementation of the DistilBertModel.

pub fn new<'p, P>(p: P, config: &DistilBertConfig) -> DistilBertModel

where P: Borrow<Path<'p>>,

Build a new DistilBertModel

Arguments

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

Example

use rust_bert::distilbert::{DistilBertConfig, DistilBertModel};
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: DistilBertModel = DistilBertModel::new(&p.root() / "distilbert", &config);

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

• DistilBertTransformerOutput containing:
  • hidden_state - Tensor of shape (batch size, sequence_length, hidden_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

use rust_bert::distilbert::{DistilBertConfig, DistilBertModel};
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()
});