28 lines
816 B
Python

"""Winogrande (official source: allenai/winogrande, winogrande_xl)."""
from ..sample import Sample
from ..registry import register_dataset
from ..spec import DatasetSpec
@register_dataset(
DatasetSpec(
name='winogrande',
source='allenai/winogrande', # official: https://huggingface.co/datasets/allenai/winogrande
subset='winogrande_xl',
split='validation',
task_type='mcq',
tags=['commonsense', 'coreference'],
description='Winogrande XL binary coreference (official).',
)
)
def winogrande():
def to_sample(record: dict) -> Sample:
return Sample(
input=record['sentence'],
choices=[record['option1'], record['option2']],
target={'1': 'A', '2': 'B'}[record['answer']],
)
return to_sample