33 lines
1.0 KiB
Python

"""OpenAI MRCR (multi-round coreference, long-context). Mirror: openai-mirror/mrcr."""
from ..sample import Sample
from ..registry import register_dataset
from ..spec import DatasetSpec
@register_dataset(
DatasetSpec(
name='openai_mrcr',
source='openai-mirror/mrcr', # OpenAI MRCR mirror on ModelScope
subset='2needle', # or 4needle / 8needle
split='test',
task_type='qa',
tags=['long_context'],
description='OpenAI MRCR long-context retrieval/coreference (community mirror).',
params={'hub': 'modelscope'},
)
)
def openai_mrcr():
def to_sample(record: dict) -> Sample:
return Sample(
input=record['prompt'],
target=str(record['answer']).strip(),
metadata={
'n_needles': record.get('n_needles'),
'total_messages': record.get('total_messages'),
'random_string_to_prepend': record.get('random_string_to_prepend'),
},
)
return to_sample