mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
689ffe5b63
* update commonsenseqa * update drop * update flores_first100 * update gsm8k * update humaneval * update lambda * update obqa * update piqa * update race * update siqa * update story_cloze * update strategyqa * update tydiqa * update winogrande * update doc * update hellaswag * fix obqa * update collections * update .zip name
34 lines
1.1 KiB
Python
34 lines
1.1 KiB
Python
import json
|
|
import os
|
|
|
|
from datasets import Dataset, DatasetDict
|
|
|
|
from opencompass.registry import LOAD_DATASET
|
|
|
|
from .base import BaseDataset
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class RaceDataset(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path: str, name: str):
|
|
dataset = {}
|
|
for split in ['validation', 'test']:
|
|
jsonl_path = os.path.join(path, split, f'{name}.jsonl')
|
|
dataset_list = []
|
|
with open(jsonl_path, 'r', encoding='utf-8') as f:
|
|
for line in f:
|
|
line = json.loads(line)
|
|
dataset_list.append({
|
|
'article': line['article'],
|
|
'question': line['question'],
|
|
'A': line['options'][0],
|
|
'B': line['options'][1],
|
|
'C': line['options'][2],
|
|
'D': line['options'][3],
|
|
'answer': line['answer'],
|
|
})
|
|
dataset[split] = Dataset.from_list(dataset_list)
|
|
return DatasetDict(dataset)
|