mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
edab1c07ba
* add ceval, gsm8k modelscope surpport * update race, mmlu, arc, cmmlu, commonsenseqa, humaneval and unittest * update bbh, flores, obqa, siqa, storycloze, summedits, winogrande, xsum datasets * format file * format file * update dataset format * support ms_dataset * udpate dataset for modelscope support * merge myl_dev and update test_ms_dataset * udpate dataset for modelscope support * update readme * update eval_api_zhipu_v2 * remove unused code * add get_data_path function * update readme * remove tydiqa japanese subset * add ceval, gsm8k modelscope surpport * update race, mmlu, arc, cmmlu, commonsenseqa, humaneval and unittest * update bbh, flores, obqa, siqa, storycloze, summedits, winogrande, xsum datasets * format file * format file * update dataset format * support ms_dataset * udpate dataset for modelscope support * merge myl_dev and update test_ms_dataset * update readme * udpate dataset for modelscope support * update eval_api_zhipu_v2 * remove unused code * add get_data_path function * remove tydiqa japanese subset * update util * remove .DS_Store * fix md format * move util into package * update docs/get_started.md * restore eval_api_zhipu_v2.py, add environment setting * Update dataset * Update * Update * Update * Update --------- Co-authored-by: Yun lin <yunlin@U-Q9X2K4QV-1904.local> Co-authored-by: Yunnglin <mao.looper@qq.com> Co-authored-by: Yun lin <yunlin@laptop.local> Co-authored-by: Yunnglin <maoyl@smail.nju.edu.cn> Co-authored-by: zhangsongyang <zhangsongyang@pjlab.org.cn>
44 lines
1.4 KiB
Python
44 lines
1.4 KiB
Python
from datasets import Dataset, DatasetDict, load_dataset
|
|
|
|
from opencompass.registry import LOAD_DATASET
|
|
from opencompass.utils import get_data_path
|
|
|
|
from .base import BaseDataset
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class RealToxicPromptsDataset(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(**kwargs):
|
|
challenging_subset = kwargs.pop('challenging_subset', False)
|
|
if kwargs['path'] == 'allenai/real-toxicity-prompts':
|
|
try:
|
|
dataset = load_dataset(**kwargs)
|
|
except ConnectionError as e:
|
|
raise ConnectionError(
|
|
f'{e} Something wrong with this dataset, '
|
|
'cannot track it online or use offline mode, '
|
|
'please set local file path directly.')
|
|
else:
|
|
path = kwargs.pop('path')
|
|
path = get_data_path(path, local_mode=True)
|
|
dataset = Dataset.from_file(path)
|
|
dataset = DatasetDict(train=dataset)
|
|
|
|
def preprocess(example):
|
|
|
|
for k, v in example['prompt'].items():
|
|
k = 'prompt_' + k
|
|
example[k] = v
|
|
del example['prompt']
|
|
|
|
return example
|
|
|
|
dataset = dataset.map(preprocess)
|
|
|
|
# return challenging subset if necessary
|
|
if challenging_subset:
|
|
return dataset.filter(lambda example: example['challenging'])
|
|
return dataset
|