CrossEncoderConfig

class lightning_ir.cross_encoder.cross_encoder_config.CrossEncoderConfig(query_length: int = 32, doc_length: int = 512, pooling_strategy: Literal['first', 'mean', 'max', 'sum'] = 'first', linear_bias: bool = False, **kwargs)[source]

Bases: LightningIRConfig

__init__(query_length: int = 32, doc_length: int = 512, pooling_strategy: Literal['first', 'mean', 'max', 'sum'] = 'first', linear_bias: bool = False, **kwargs)[source]

Configuration class for a cross-encoder model

Parameters:

  • query_length (int, optional) – Maximum query length, defaults to 32

  • doc_length (int, optional) – Maximum document length, defaults to 512

  • pooling_strategy (Literal['first', 'mean', 'max', 'sum'], optional) – Pooling strategy to aggregate the contextualized embeddings into a single vector for computing a relevance score, defaults to “first”

  • linear_bias (bool, optional) – Whether to use a bias in the prediction linear layer, defaults to False

Methods

__init__([query_length, doc_length, ...])

Configuration class for a cross-encoder model

Attributes

model_type

Model type for cross-encoder models.
backbone_model_type: str | None = None

Backbone model type for the configuration. Set by LightningIRModelClassFactory().

classmethod from_pretrained(pretrained_model_name_or_path: str | Path, *args, **kwargs) → LightningIRConfig

Loads the configuration from a pretrained model. Wraps the transformers.PretrainedConfig.from_pretrained

Parameters:

pretrained_model_name_or_path (str | Path) – Pretrained model name or path

Raises:

ValueError – If pre_trained_model_name_or_path is not a Lightning IR model and no LightningIRConfig is passed

Returns:

Derived LightningIRConfig class

Return type:

LightningIRConfig

get_tokenizer_kwargs(Tokenizer: Type[LightningIRTokenizer]) → Dict[str, Any]

Returns the keyword arguments for the tokenizer. This method is used to pass the configuration parameters to the tokenizer.

Parameters:

Tokenizer (Type[LightningIRTokenizer]) – Class of the tokenizer to be used

Returns:

Keyword arguments for the tokenizer

Return type:

Dict[str, Any]

model_type: str = 'cross-encoder'

Model type for cross-encoder models.

to_dict() → Dict[str, Any]

Overrides the transformers.PretrainedConfig.to_dict method to include the added arguments and the backbone model type.

Returns:

Configuration dictionary

Return type:

Dict[str, Any]