SpladeConfig

class lightning_ir.models.splade.SpladeConfig(query_pooling_strategy: Literal['first', 'mean', 'max', 'sum'] | None = 'max', doc_pooling_strategy: Literal['first', 'mean', 'max', 'sum'] | None = 'max', projection: Literal['linear', 'linear_no_bias', 'mlm'] | None = 'mlm', sparsification: Literal['relu', 'relu_log'] | None = 'relu_log', embedding_dim: int = 30522, **kwargs)[source]

Bases: BiEncoderConfig

__init__(query_pooling_strategy: Literal['first', 'mean', 'max', 'sum'] | None = 'max', doc_pooling_strategy: Literal['first', 'mean', 'max', 'sum'] | None = 'max', projection: Literal['linear', 'linear_no_bias', 'mlm'] | None = 'mlm', sparsification: Literal['relu', 'relu_log'] | None = 'relu_log', embedding_dim: int = 30522, **kwargs) → None[source]

Methods

`__init__`([query_pooling_strategy, ...])
`from_dict`(config_dict, args, *kwargs)	Loads the configuration from a dictionary.
`from_pretrained`(...)
`get_config_dict`(...)
`save_pretrained`(save_directory[, push_to_hub])
`to_added_args_dict`()	Outputs a dictionary of the added arguments.
`to_dict`()
`to_tokenizer_dict`()	Outputs a dictionary of the tokenizer arguments.

Attributes

`ADDED_ARGS`	Arguments added to the configuration.
`TOKENIZER_ARGS`	Arguments for the tokenizer.
`backbone_model_type`	Backbone model type for the configuration.
`model_type`	Model type for the configuration.

classmethod from_dict(config_dict: Dict[str, Any], *args, **kwargs) → LightningIRConfig

Loads the configuration from a dictionary. Wraps the transformers.PretrainedConfig.from_dict method to return a derived LightningIRConfig class. See LightningIRConfigClassFactory for more details.

Parameters:: config_dict (Dict[str, Any]) – Configuration dictionary
Raises:: ValueError – If the model type does not match the configuration model type
Returns:: Derived LightningIRConfig class
Return type:: LightningIRConfig

to_added_args_dict() → Dict[str, Any]

Outputs a dictionary of the added arguments.

Returns:: Added arguments
Return type:: Dict[str, Any]

to_tokenizer_dict() → Dict[str, Any]

Outputs a dictionary of the tokenizer arguments.

Returns:: Tokenizer arguments
Return type:: Dict[str, Any]