Sparsifier

class lightning_ir.modeling_utils.embedding_post_processing.Sparsifier(config: LightningIRConfig)

Bases: Module

Applies sparsification to the embeddings based on the sparsification strategy defined in the configuration.

__init__(config: LightningIRConfig) → None

Initializes the sparsifier.

Parameters:

config (LightningIRConfig) – Configuration containing the sparsification strategy to apply

Methods

__init__(config)	Initializes the sparsifier.
forward(embeddings)	Applies optional sparsification to the embeddings.

Attributes

training

forward(embeddings: Tensor) → Tensor

Applies optional sparsification to the embeddings.

Parameters:

embeddings (torch.Tensor) – Query, document, or joint query-document embeddings

Returns:

(Optionally) sparsified embeddings

Return type:

torch.Tensor

Raises:

ValueError – If an unknown sparsification strategy is passed