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
51 lines
1.7 KiB
Python
51 lines
1.7 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 storyclozeDataset(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path, lang):
|
|
dataset_list = []
|
|
for split in ['train', 'eval']:
|
|
split_path = os.path.join(path, f'{lang}_{split}.jsonl')
|
|
with open(split_path, 'r', encoding='utf-8') as f:
|
|
for line in f:
|
|
line = json.loads(line)
|
|
line['context'] = ' '.join([
|
|
line['input_sentence_1'], line['input_sentence_2'],
|
|
line['input_sentence_3'], line['input_sentence_4']
|
|
])
|
|
dataset_list.append(line)
|
|
dataset_list = Dataset.from_list(dataset_list)
|
|
return DatasetDict({'test': dataset_list})
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class storyclozeDataset_V2(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path, lang):
|
|
dataset_list = []
|
|
for split in ['train', 'eval']:
|
|
split_path = os.path.join(path, f'{lang}_{split}.jsonl')
|
|
with open(split_path, 'r', encoding='utf-8') as f:
|
|
for line in f:
|
|
line = json.loads(line)
|
|
line['context'] = ' '.join([
|
|
line['input_sentence_1'], line['input_sentence_2'],
|
|
line['input_sentence_3'], line['input_sentence_4']
|
|
])
|
|
line['answer_right_ending'] = ' AB'[
|
|
line['answer_right_ending']]
|
|
dataset_list.append(line)
|
|
dataset_list = Dataset.from_list(dataset_list)
|
|
return dataset_list
|