30 lines
897 B
Python

"""MMLU-Pro (official source: TIGER-Lab/MMLU-Pro)."""
from ..sample import Sample
from ..registry import register_dataset
from ..spec import DatasetSpec
@register_dataset(
DatasetSpec(
name='mmlu_pro',
source='TIGER-Lab/MMLU-Pro', # official: https://huggingface.co/datasets/TIGER-Lab/MMLU-Pro
split='test',
few_shot_split='validation',
few_shot_num=5,
task_type='mcq',
tags=['knowledge'],
description='MMLU-Pro: 10-option harder MMLU (official).',
)
)
def mmlu_pro():
def to_sample(record: dict) -> Sample:
return Sample(
input=record['question'],
choices=list(record['options']),
target=str(record['answer']).strip(), # already a letter
metadata={'category': record.get('category'), 'question_id': record.get('question_id')},
)
return to_sample