2023-08-21 14:15:20 +08:00
|
|
|
from datasets import Dataset, load_dataset
|
|
|
|
|
|
|
|
from opencompass.registry import LOAD_DATASET
|
[Feature] Support ModelScope datasets (#1289)
* 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>
2024-07-29 13:48:32 +08:00
|
|
|
from opencompass.utils import get_data_path
|
2023-08-21 14:15:20 +08:00
|
|
|
|
|
|
|
from ..base import BaseDataset
|
|
|
|
|
|
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
|
|
class LongBenchpassage_countDataset(BaseDataset):
|
|
|
|
|
|
|
|
@staticmethod
|
2024-09-06 15:50:12 +08:00
|
|
|
def load(path: str, name: str):
|
|
|
|
path = get_data_path(path)
|
|
|
|
dataset = load_dataset(path=path,
|
|
|
|
name=name,
|
|
|
|
data_dir=path,
|
|
|
|
trust_remote_code=True)
|
2023-08-21 14:15:20 +08:00
|
|
|
split = 'test'
|
|
|
|
raw_data = []
|
|
|
|
for i in range(len(dataset[split])):
|
|
|
|
context = dataset[split]['context'][i]
|
|
|
|
answers = dataset[split]['answers'][i]
|
|
|
|
raw_data.append({'context': context, 'answers': answers})
|
|
|
|
dataset[split] = Dataset.from_list(raw_data)
|
|
|
|
return dataset
|