[−][src]Struct rust_bert::gpt2::Gpt2Model
GPT2 Base model
Base architecture for GPT2 model. Usually complemented with a task-specific head, such as a language model head. It is made of the following blocks:
wte
:token
embeddingswpe
:position
embeddingsh
: Encoder (transformer) made of a vector of layers. Each layer is made of a multi-head attention layer, layer-normalization layers and a MLP made of linear layers.output_past
: flag indicating if the model should return a past state. This can be fed back to the model to improve the quality of text generated.output_hidden_states
: flag indicating if the model should return all hidden states (as opposed to only the last layer)output_attentions
: flag indicating if the model should return activation weights
Methods
impl Gpt2Model
[src]
pub fn new(p: &Path, config: &Gpt2Config) -> Gpt2Model
[src]
Build a new Gpt2Model
Arguments
p
- Variable store path for the root of the GPT2 modelconfig
-Gpt2Config
object defining the model architecture
Example
use tch::{nn, Device}; use rust_bert::Config; use std::path::Path; use rust_bert::gpt2::{Gpt2Config, Gpt2Model}; let config_path = Path::new("path/to/config.json"); let device = Device::Cpu; let p = nn::VarStore::new(device); let config = Gpt2Config::from_file(config_path); let gpt2: Gpt2Model = Gpt2Model::new(&(&p.root() / "gpt2"), &config);
pub fn forward_t(
&self,
input_ids: &Option<Tensor>,
layer_past: &Option<Vec<Tensor>>,
attention_mask: &Option<Tensor>,
token_type_ids: &Option<Tensor>,
position_ids: &Option<Tensor>,
input_embeds: &Option<Tensor>,
train: bool
) -> Result<(Tensor, Option<Vec<Tensor>>, Option<Vec<Tensor>>, Option<Vec<Tensor>>), &'static str>
[src]
&self,
input_ids: &Option<Tensor>,
layer_past: &Option<Vec<Tensor>>,
attention_mask: &Option<Tensor>,
token_type_ids: &Option<Tensor>,
position_ids: &Option<Tensor>,
input_embeds: &Option<Tensor>,
train: bool
) -> Result<(Tensor, Option<Vec<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
)layer_past
- Optional vector of length n_layer containing the past keys and values of each layer of shape (2, batch size, number of heads, past_sequence_length, hidden size per head). When provided, these are concatenated with the current input keys and values.attention_mask
- Optional mask of shape (batch size, sequence_length). Masked position have value 0, non-masked value 1. If None set to 1input_embeds
- Optional pre-computed input embeddings of shape (batch size, sequence_length, hidden_size). If None, input ids must be provided (seeinput_ids
)token_type_ids
- Optional token type ids used to indicate the portion of the input the token belongs to. If not None, token type embeddings will be added to the token and position embeddings.position_ids
- Optional position ids of shape (batch size, sequence_length). If None, will be incremented starting from the length of the past input.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) representing the activations of the last hidden statepast
-Option<Vec<Tensor>>
of length n_layer containing the past keys and values of each layer of shape (2, batch size, number of heads, past_sequence_length, hidden size per head)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
use rust_bert::gpt2::{Gpt2Model, Gpt2Config}; let (batch_size, sequence_length, past_sequence_length) = (64, 128, 56); let input_tensor = Tensor::rand(&[batch_size, sequence_length], (Int64, device)); let mut past: Vec<Tensor> = Vec::with_capacity(config.n_layer as usize); for _ in 0..config.n_layer as usize { past.push(Tensor::rand(&[2, batch_size, config.n_head, past_sequence_length, config.n_embd / config.n_head], (Double, device))) } let attention_mask = Tensor::zeros(&[batch_size, sequence_length], (Int64, device)); let token_type_ids = Tensor::ones(&[batch_size, sequence_length], (Int64, device)); let position_ids = Tensor::arange(sequence_length, (Int64, device)).expand(&[batch_size, sequence_length], true); let (output, past, hidden_states, attentions) = no_grad(|| { gpt2_model .forward_t(&Some(input_tensor), &Some(past), &Some(attention_mask), &Some(token_type_ids), &Some(position_ids), &None, false).unwrap() });
Auto Trait Implementations
impl !RefUnwindSafe for Gpt2Model
impl !Send for Gpt2Model
impl !Sync for Gpt2Model
impl Unpin for Gpt2Model
impl !UnwindSafe for Gpt2Model
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>,