langtest.transform.performance.BasePerformance#

class BasePerformance#

Bases: ABC

Abstract base class for implementing a model performance.

This class defines the interface for implementing a model performance.

None#

__init__()#

Methods

__init__()
async_run(sample_list, model, **kwargs)	Creates a task to run the model performance.
run(sample_list, model, **kwargs)	Abstract method that implements the model performance.
time_measure(start_time, sample_list, tokens)
transform()	Abstract method that transforms the sample data based on the implemented model performance.

Attributes

TOKENS
alias_name
test_types

async classmethod async_run(sample_list: List[Sample], model: ModelAPI, **kwargs)#

Creates a task to run the model performance.

Parameters:

• sample_list (List[Sample]) – The input data to be transformed.

• model (ModelAPI) – The model to be used for evaluation.

• **kwargs – Additional arguments to be passed to the model performance.

Returns:

The task that runs the model performance.

Return type:

asyncio.Task

abstract async static run(sample_list: List[Sample], model: ModelAPI, **kwargs) → List[Sample]#

Abstract method that implements the model performance.

Parameters:

• sample_list (List[Sample]) – The input data to be transformed.

• model (ModelAPI) – The model to be used for evaluation.

• **kwargs – Additional arguments to be passed to the model performance.

Returns:

The transformed data based on the implemented model performance.

Return type:

List[Sample]

abstract static transform()#

Abstract method that transforms the sample data based on the implemented model performance.

Parameters:

• params (dict) – The input data to be transformed.

• *args – Additional positional arguments.

• **kwargs – Additional keyword arguments.

Returns:

The transformed data based on the implemented model performance.

Return type:

List[Sample]

Raises:

NotImplementedError – This method must be implemented in the derived class.