← back to Exo
.typings/mlx/nn/layers/transformer.pyi
169 lines
"""
This type stub file was generated by pyright.
"""
from typing import Any, Callable, Optional
import mlx.core as mx
from base import Module
class MultiHeadAttention(Module):
"""Implements the scaled dot product attention with multiple heads.
Given inputs for queries, keys and values the ``MultiHeadAttention``
produces new values by aggregating information from the input values
according to the similarities of the input queries and keys.
All inputs as well as the output are linearly projected without biases by
default.
``MultiHeadAttention`` also takes an optional additive attention mask that
should be broadcastable with ``(batch, num_heads, # queries, # keys)``. The
mask should have ``-inf`` or very large negative numbers at the positions
that should *not* be attended to.
Args:
dims (int): The model dimensions. This is also the default
value for the queries, keys, values, and the output.
num_heads (int): The number of attention heads to use.
query_input_dims (int, optional): The input dimensions of the queries.
Default: ``dims``.
key_input_dims (int, optional): The input dimensions of the keys.
Default: ``dims``.
value_input_dims (int, optional): The input dimensions of the values.
Default: ``key_input_dims``.
value_dims (int, optional): The dimensions of the values after the
projection. Default: ``dims``.
value_output_dims (int, optional): The dimensions the new values will
be projected to. Default: ``dims``.
bias (bool, optional): Whether or not to use a bias in the projections.
Default: ``False``.
"""
def __init__(
self,
dims: int,
num_heads: int,
query_input_dims: Optional[int] = ...,
key_input_dims: Optional[int] = ...,
value_input_dims: Optional[int] = ...,
value_dims: Optional[int] = ...,
value_output_dims: Optional[int] = ...,
bias: bool = ...,
) -> None: ...
def __call__(
self, queries: mx.array, keys: mx.array, values: mx.array, mask: mx.array = ...
) -> mx.array: ...
@staticmethod
def create_additive_causal_mask(N: int, dtype: mx.Dtype = ...) -> mx.array: ...
class TransformerEncoderLayer(Module):
def __init__(
self,
dims: int,
num_heads: int,
mlp_dims: Optional[int] = ...,
dropout: float = ...,
activation: Callable[[Any], Any] = ...,
norm_first: bool = ...,
) -> None: ...
def __call__(self, x: mx.array, mask: mx.array) -> mx.array: ...
class TransformerEncoder(Module):
def __init__(
self,
num_layers: int,
dims: int,
num_heads: int,
mlp_dims: Optional[int] = ...,
dropout: float = ...,
activation=...,
norm_first: bool = ...,
checkpoint: bool = ...,
) -> None: ...
def __call__(self, x: mx.array, mask: mx.array) -> mx.array: ...
class TransformerDecoderLayer(Module):
def __init__(
self,
dims: int,
num_heads: int,
mlp_dims: Optional[int] = ...,
dropout: float = ...,
activation: Callable[[Any], Any] = ...,
norm_first: bool = ...,
) -> None: ...
def __call__(self, x: mx.array, memory, x_mask, memory_mask) -> mx.array: ...
class TransformerDecoder(Module):
def __init__(
self,
num_layers: int,
dims: int,
num_heads: int,
mlp_dims: Optional[int] = ...,
dropout: float = ...,
activation=...,
norm_first: bool = ...,
checkpoint: bool = ...,
) -> None: ...
def __call__(self, x: mx.array, memory, x_mask, memory_mask) -> mx.array: ...
class Transformer(Module):
"""
Implements a standard Transformer model.
The implementation is based on `Attention Is All You Need
<https://arxiv.org/abs/1706.03762>`_.
The Transformer model contains an encoder and a decoder. The encoder
processes the input sequence and the decoder generates the output sequence.
The interaction between encoder and decoder happens through the attention
mechanism.
Args:
dims (int, optional): The number of expected features in the
encoder/decoder inputs. Default: ``512``.
num_heads (int, optional): The number of attention heads. Default:
``8``.
num_encoder_layers (int, optional): The number of encoder layers in the
Transformer encoder. Default: ``6``.
num_decoder_layers (int, optional): The number of decoder layers in the
Transformer decoder. Default: ``6``.
mlp_dims (int, optional): The hidden dimension of the MLP block in each
Transformer layer. Defaults to ``4*dims`` if not provided. Default:
``None``.
dropout (float, optional): The dropout value for the Transformer
encoder and decoder. Dropout is used after each attention layer and
the activation in the MLP layer. Default: ``0.0``.
activation (function, optional): the activation function for the MLP
hidden layer. Default: :func:`relu`.
custom_encoder (nn.Module, optional): A custom encoder to replace the
standard Transformer encoder. Default: ``None``.
custom_decoder (nn.Module, optional): A custom decoder to replace the
standard Transformer decoder. Default: ``None``.
norm_first (bool, optional): if ``True``, encoder and decoder layers
will perform layer normalization before attention and MLP
operations, otherwise after. Default: ``True``.
checkpoint (bool, optional): if ``True`` perform gradient checkpointing
to reduce the memory usage at the expense of more computation.
Default: ``False``.
"""
def __init__(
self,
dims: int = ...,
num_heads: int = ...,
num_encoder_layers: int = ...,
num_decoder_layers: int = ...,
mlp_dims: Optional[int] = ...,
dropout: float = ...,
activation: Callable[[Any], Any] = ...,
custom_encoder: Optional[Any] = ...,
custom_decoder: Optional[Any] = ...,
norm_first: bool = ...,
checkpoint: bool = ...,
) -> None: ...
def __call__(
self, src, tgt, src_mask, tgt_mask, memory_mask
) -> mx.array: # -> array | Any:
...