Adapters

modelgenerator.adapters.MLPAdapter

Bases: Sequential, TokenAdapter

Multi-layer perceptron (MLP) adapter.

Parameters:

Name	Type	Description	Default
in_features	int	Number of features of the input	required
out_features	int	Number of features of the output	required
hidden_sizes	List[int]	List of the hidden feature dimensions. Defaults to [].	[]
activation_layer	Callable[..., Module]	Activation function. Defaults to torch.nn.Tanh.	Tanh
bias	bool	Whether to use bias in the linear layer. Defaults to True	True
dropout	float	The probability for the dropout layer. Defaults to 0.0	0.0
dropout_in_middle	bool	Whether to use dropout in the middle layers. Defaults to True	True

modelgenerator.adapters.MLPAdapterWithoutOutConcat

Bases: Module, TokenAdapter

Multi-layer perceptron (MLP) adapter without outer concatenate

This class is generally used in PairwiseTokenClassification. The following two implementations are equivalent: 1. hidden_states -> outer_concat -> MLPAdapter 2. hidden_states -> MLPAdapterWithoutOutConcat MLPAdapterWithoutOutConcat avoids the large memory consumption of outer_concat

Parameters:

Name	Type	Description	Default
in_features	int	Number of features of the input	required
out_features	int	Number of features of the output	required
hidden_sizes	List[int]	List of the hidden feature dimensions. Defaults to [].	[]
activation_layer	Callable[..., Module]	Activation function. Defaults to torch.nn.Tanh.	Tanh
bias	bool	Whether to use bias in the linear layer. Defaults to True	True
dropout	float	The probability for the dropout layer. Defaults to 0.0	0.0
dropout_in_middle	bool	Whether to use dropout in the middle layers. Defaults to True	True

modelgenerator.adapters.LinearAdapter

Bases: MLPAdapter

Simple linear adapter for a 1D embedding

Parameters:

Name	Type	Description	Default
in_features	int	Number of input features	required
out_features	int	Number of output features	required

modelgenerator.adapters.LinearCLSAdapter

Bases: Module, SequenceAdapter

Simple linear adapter for a 1D embedding

Parameters:

Name	Type	Description	Default
in_features	int	Number of input features	required
out_features	int	Number of output features	required

modelgenerator.adapters.LinearTransformerAdapter

Bases: Module, SequenceAdapter

Transformer adapter

Note: Sopport cls_pooling only.

Parameters:

Name	Type	Description	Default
embed_dim	int	Hidden size	required
out_features	int	Number of output features	required

modelgenerator.adapters.ConditionalLMAdapter

Bases: Module, ConditionalGenerationAdapter

Conditional sequence adapter

Parameters:

Name	Type	Description	Default
in_features	int	Number of input features	required
embed_dim	int	Hidden size	required
seq_len	int	Sequence length	required

modelgenerator.adapters.MMFusionSeqAdapter

Bases: Module, FusionAdapter

Multimodal embeddings fusion with SequenceAdapter.

Note: Accept 2-3 sequence embeddings as input and fused them into a multimodal embedding for the adpter

Parameters:

Name	Type	Description	Default
out_features	int	Number of output features	required
input_size	int	number of input features for the first modality	required
input_size_1	int	number of input features for the second modality	required
input_size_2	(int, optinal)	number of input features for the third modality	None
fusion	(Callable, Module)	The callable that returns a fusion module. Defaults to CrossAttentionFusion.	CrossAttentionFusion
adapter	Callable[[int, int], SequenceAdapter]	The callable that returns an adapter. Defaults to LinearCLSAdapter.	LinearCLSAdapter

modelgenerator.adapters.MMFusionTokenAdapter

Bases: Module, FusionAdapter

Multimodal embeddings fusion with TokenAdapter, fuse embeddings at token level

Note: Accept 2-3 sequence embeddings as input and fused them into a multimodal embedding for the adpter

Parameters:

Name	Type	Description	Default
out_features	int	Number of output features	required
input_size	int	number of input features for the first modality	required
input_size_1	int	number of input features for the second modality	required
input_size_2	(int, optinal)	number of input features for the third modality	None
fusion	(Callable, Module)	The callable that returns a fusion module. Defaults to CrossAttentionFusion.	CrossAttentionFusion
adapter	Callable[[int, int], TokenAdapter]	The callable that returns an adapter. Defaults to MLPAdapter.	MLPAdapter