2023-09-12 19:16:41 +08:00
|
|
|
import json
|
|
|
|
import os.path as osp
|
|
|
|
|
|
|
|
from datasets import Dataset, DatasetDict
|
|
|
|
|
|
|
|
from opencompass.registry import LOAD_DATASET
|
|
|
|
|
|
|
|
from .base import BaseDataset
|
|
|
|
|
|
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
|
|
class CMBDataset(BaseDataset):
|
|
|
|
|
|
|
|
@staticmethod
|
|
|
|
def load(path: str):
|
2023-10-27 20:31:22 +08:00
|
|
|
with open(osp.join(path, 'val.json'), 'r', encoding='utf-8') as f:
|
2023-09-12 19:16:41 +08:00
|
|
|
val_data = json.load(f)
|
2023-11-13 00:09:05 +08:00
|
|
|
for d in val_data:
|
|
|
|
d['option_str'] = '\n'.join(
|
|
|
|
[f'{k}. {v}' for k, v in d['option'].items() if len(v) > 1])
|
|
|
|
val_dataset = Dataset.from_list(val_data)
|
2023-09-12 19:16:41 +08:00
|
|
|
|
2023-11-13 00:09:05 +08:00
|
|
|
with open(osp.join(path, 'test.json'), 'r', encoding='utf-8') as f:
|
|
|
|
test_data = json.load(f)
|
|
|
|
for d in test_data:
|
|
|
|
d['option_str'] = '\n'.join(
|
|
|
|
[f'{k}. {v}' for k, v in d['option'].items() if len(v) > 1])
|
2024-04-30 00:33:43 +08:00
|
|
|
d['answer'] = 'NULL'
|
2023-09-12 19:16:41 +08:00
|
|
|
test_dataset = Dataset.from_list(test_data)
|
2023-11-13 00:09:05 +08:00
|
|
|
|
|
|
|
return DatasetDict({'val': val_dataset, 'test': test_dataset})
|