Struct rust_bert::deberta::DebertaModel

pub struct DebertaModel { /* private fields */ }

DeBERTa Base model

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

• embeddings: DeBERTa embeddings
• encoder: DeBERTaEncoder (transformer) made of a vector of layers.

Implementations

impl DebertaModel

pub fn new<'p, P>(p: P, config: &DebertaConfig) -> DebertaModelwhere
    P: Borrow<Path<'p>>,

Build a new DebertaModel

Arguments

• p - Variable store path for the root of the BERT model
• config - DebertaConfig object defining the model architecture and decoder status

Example

use rust_bert::deberta::{DebertaConfig, DebertaModel};
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 = DebertaConfig::from_file(config_path);
let model: DebertaModel = DebertaModel::new(&p.root() / "deberta", &config);

pub fn forward_t(
    &self,
    input_ids: Option<&Tensor>,
    attention_mask: Option<&Tensor>,
    token_type_ids: Option<&Tensor>,
    position_ids: Option<&Tensor>,
    input_embeds: Option<&Tensor>,
    train: bool
) -> Result<DebertaEncoderOutput, 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)
• attention_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)
• train - boolean flag to turn on/off the dropout layers in the model. Should be set to false for inference.

Returns

• DebertaOutput 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

let (batch_size, sequence_length) = (64, 128);
let input_tensor = Tensor::rand(&[batch_size, sequence_length], (Kind::Int64, device));
let attention_mask = Tensor::ones(&[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(|| {
    model
        .forward_t(
            Some(&input_tensor),
            Some(&attention_mask),
            Some(&token_type_ids),
            Some(&position_ids),
            None,
            false,
        )
        .unwrap()
});