zhangyiss/mlx
1
0
Fork 0
mirror of https://github.com/ml-explore/mlx.git synced 2025-08-20 10:27:41 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

precommit

Browse Source
This commit is contained in:
junwoo-yun 2023-12-27 02:16:26 +08:00
parent bee11e79d9
commit 0372cbbcbf
1 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
python/mlx/nn/layers/transformer.py
View File

@ -147,6 +147,7 @@ class TransformerEncoderLayer(Module):
return y
class TransformerEncoder(Module):
def __init__(
self,
@ -279,13 +280,13 @@ class Transformer(Module):
num_encoder_layers (int): The number of sub-encoder-layers in the Transformer encoder (default: 6)
num_decoder_layers (int): The number of sub-decoder-layers in the Transformer decoder (default: 6)
mlp_dims (Optional[int]): The dimensionality of the feedforward network model in each Transformer layer,
Defaults to 4*dims if not provided (default: None).
Defaults to 4*dims if not provided (default: None)
dropout (float): The dropout value for Transformer encoder/decoder (default: 0.0)
activation (Callable[[Any], Any]): the activation function of encoder/decoder intermediate layer (default: relu)
custom_encoder (Optional[Any]): A custom encoder to replace the standard Transformer encoder (default: None)
custom_decoder (Optional[Any]): A custom decoder to replace the standard Transformer decoder (default: None)
norm_first (bool): if ``True``, encoder and decoder layers will perform LayerNorms before
other attention and feedforward operations, otherwise after. (default: False)
norm_first (bool): if ``True``, encoder and decoder layers will perform LayerNorms before
other attention and feedforward operations, otherwise after (default: False)
"""
def __init__(