pub struct TransformerDecoderBlock<const MODEL_DIM: usize, const NUM_HEADS: usize, const FF_DIM: usize> {
    pub self_attn: MultiHeadAttention<MODEL_DIM, NUM_HEADS>,
    pub norm1: LayerNorm1D<MODEL_DIM>,
    pub mh_attn: MultiHeadAttention<MODEL_DIM, NUM_HEADS>,
    pub norm2: LayerNorm1D<MODEL_DIM>,
    pub ff: Residual<(Linear<M, F>, ReLU, Linear<F, M>)>,
    pub norm3: LayerNorm1D<MODEL_DIM>,
}
Expand description

Requires Nightly A transformer decoder block. Different than the normal transformer block as this self attention accepts an additional sequence from the encoder.

Generics

  • MODEL_DIM: The size of query/key/value tensors. Given to MultiHeadAttention.
  • NUM_HEADS: The number of heads in MultiHeadAttention.
  • FF_DIM: The size of the hidden layer in the feedforward network.

Pytorch equivalent:

decoder = torch.nn.TransformerDecoderLayer(
   EMBED_DIM, NUM_HEADS, dim_feedforward=FF_DIM, batch_first=True, dropout=0.0
)

TODO: Doctests

Fields

self_attn: MultiHeadAttention<MODEL_DIM, NUM_HEADS>norm1: LayerNorm1D<MODEL_DIM>mh_attn: MultiHeadAttention<MODEL_DIM, NUM_HEADS>norm2: LayerNorm1D<MODEL_DIM>ff: Residual<(Linear<M, F>, ReLU, Linear<F, M>)>norm3: LayerNorm1D<MODEL_DIM>

Trait Implementations

Updates self given the GradientProvider. When any parameters that are NOT present in G, then this function should add the tensor’s UniqueId to UnusedTensors. Read more
Returns a copy of the value. Read more
Performs copy-assignment from source. Read more
Formats the value using the given formatter. Read more
Returns the “default value” for a type. Read more
Reads this object from a ZipArchive. r with a base filename of filename_prefix. Read more
Loads data from a .npz zip archive at the specified path. Read more
The type that this unit produces given Input.
Forward Input through the module and produce Module::Output. Read more
Mutate the unit’s parameters using rand::Rng. Each implementor of this trait decides how the parameters are initialized. In fact, some impls may not even use the rng. Read more
Write this object into ZipWriter w with a base filename of filename_prefix. Read more
Save this object into the .npz file determined located at path. Read more

Auto Trait Implementations

Blanket Implementations

Gets the TypeId of self. Read more
Immutably borrows from an owned value. Read more
Mutably borrows from an owned value. Read more

Returns the argument unchanged.

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

The resulting type after obtaining ownership.
Creates owned data from borrowed data, usually by cloning. Read more
Uses borrowed data to replace owned data, usually by cloning. Read more
The type returned in the event of a conversion error.
Performs the conversion.
The type returned in the event of a conversion error.
Performs the conversion.