LightningIRConfig

class lightning_ir.base.config.LightningIRConfig(*args, query_length: int = 32, doc_length: int = 512, **kwargs)

Bases: object

The configuration class to instantiate a LightningIR model. Acts as a mixin for the transformers.PretrainedConfig class.

__init__(*args, query_length: int = 32, doc_length: int = 512, **kwargs)

Initializes the configuration.

Parameters:

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

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

Methods

__init__(*args[, query_length, doc_length])	Initializes the configuration.
from_dict(config_dict, *args, **kwargs)	Loads the configuration from a dictionary.
from_pretrained(...)
to_added_args_dict()	Outputs a dictionary of the added arguments.
to_dict()	Overrides the transformers.PretrainedConfig.to_dict method to include the added arguments and the backbone model type.
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.

ADDED_ARGS: Set[str] = {'doc_length', 'query_length'}

Arguments added to the configuration.

TOKENIZER_ARGS: Set[str] = {'doc_length', 'query_length'}

Arguments for the tokenizer.

backbone_model_type: str | None = None

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

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

model_type = 'lightning-ir'

Model type for the configuration.

to_added_args_dict() → Dict[str, Any]

Outputs a dictionary of the added arguments.

Returns:

Added arguments

Return type:

Dict[str, Any]

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_tokenizer_dict() → Dict[str, Any]

Outputs a dictionary of the tokenizer arguments.

Returns:

Tokenizer arguments

Return type:

Dict[str, Any]