24 lines
758 B
Python

"""BIG-Bench Hard (standard mirror: lukaemon/bbh; original: github.com/suzgunmirac/BIG-Bench-Hard)."""
from ..sample import Sample
from ..registry import register_dataset
from ..spec import DatasetSpec
@register_dataset(
DatasetSpec(
name='bbh',
source='lukaemon/bbh', # https://huggingface.co/datasets/lukaemon/bbh
subset='boolean_expressions', # 27 subtasks; override with --subset <subtask>
split='test',
task_type='qa',
tags=['reasoning'],
description='BIG-Bench Hard, 27 subtasks (each subset caches under bbh/<hash>).',
)
)
def bbh():
def to_sample(record: dict) -> Sample:
return Sample(input=record['input'], target=str(record['target']).strip())
return to_sample