BiEncoderConfig

class lightning_ir.bi_encoder.bi_encoder_config.BiEncoderConfig(query_length: int = 32, doc_length: int = 512, similarity_function: Literal['cosine', 'dot'] = 'dot', normalize: bool = False, sparsification: Literal['relu', 'relu_log'] | None = None, add_marker_tokens: bool = False, **kwargs)[source]

Bases: LightningIRConfig

Configuration class for a bi-encoder model.

__init__(query_length: int = 32, doc_length: int = 512, similarity_function: Literal['cosine', 'dot'] = 'dot', normalize: bool = False, sparsification: Literal['relu', 'relu_log'] | None = None, add_marker_tokens: bool = False, **kwargs)[source]

A bi-encoder model encodes queries and documents separately and computes a relevance score based on the similarity of the query and document embeddings. Normalization and sparsification can be applied to the embeddings before computing the similarity score.

Parameters:

  • query_length (int) – Maximum query length. Defaults to 32.

  • doc_length (int) – Maximum document length. Defaults to 512.

  • similarity_function (Literal['cosine', 'dot']) – Similarity function to compute scores between query and document embeddings. Defaults to “dot”.

  • normalize (bool) – Whether to normalize query and document embeddings. Defaults to False.

  • sparsification (Literal['relu', 'relu_log'] | None) – Whether and which sparsification function to apply. Defaults to None.

  • add_marker_tokens (bool) – Whether to prepend extra marker tokens [Q] / [D] to queries / documents. Defaults to False.

Methods

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

A bi-encoder model encodes queries and documents separately and computes a relevance score based on the similarity of the query and document embeddings.

to_diff_dict()

Removes all attributes from the configuration that correspond to the default config attributes for better readability, while always retaining the config attribute from the class.

Attributes

model_type

Model type for bi-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.

Returns:

Derived LightningIRConfig class.

Return type:

LightningIRConfig

Raises:

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

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 = 'bi-encoder'

Model type for bi-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]

to_diff_dict() → dict[str, Any][source]

Removes all attributes from the configuration that correspond to the default config attributes for better readability, while always retaining the config attribute from the class. Serializes to a Python dictionary.

Returns:

Dictionary of all the attributes that make up this configuration instance.

Return type:

dict[str, Any]