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>
72 lines
2.2 KiB
Python
72 lines
2.2 KiB
Python
import json
|
|
from os import environ
|
|
|
|
from datasets import Dataset
|
|
|
|
from opencompass.registry import LOAD_DATASET
|
|
from opencompass.utils import get_data_path
|
|
|
|
from .base import BaseDataset
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class CMNLIDataset(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path, local_mode: bool = False):
|
|
path = get_data_path(path, local_mode=local_mode)
|
|
if environ.get('DATASET_SOURCE') == 'ModelScope':
|
|
from modelscope import MsDataset
|
|
ms_dataset = MsDataset.load(path, split='dev')
|
|
data = []
|
|
for line in ms_dataset:
|
|
row = line
|
|
if line['label'] == '-':
|
|
continue
|
|
data.append(row)
|
|
else:
|
|
data = []
|
|
with open(path, 'r', encoding='utf-8') as f:
|
|
for line in f:
|
|
line = json.loads(line)
|
|
if line['label'] == '-':
|
|
continue
|
|
data.append(line)
|
|
return Dataset.from_list(data)
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class CMNLIDatasetV2(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path, local_mode: bool = False):
|
|
path = get_data_path(path, local_mode=local_mode)
|
|
if environ.get('DATASET_SOURCE') == 'ModelScope':
|
|
from modelscope import MsDataset
|
|
ms_dataset = MsDataset.load(path, split='dev')
|
|
data = []
|
|
for line in ms_dataset:
|
|
row = line
|
|
if line['label'] == '-':
|
|
continue
|
|
row['label'] = {
|
|
'entailment': 'A',
|
|
'contradiction': 'B',
|
|
'neutral': 'C',
|
|
}[line['label']]
|
|
data.append(row)
|
|
else:
|
|
data = []
|
|
with open(path, 'r', encoding='utf-8') as f:
|
|
for line in f:
|
|
line = json.loads(line)
|
|
if line['label'] == '-':
|
|
continue
|
|
line['label'] = {
|
|
'entailment': 'A',
|
|
'contradiction': 'B',
|
|
'neutral': 'C',
|
|
}[line['label']]
|
|
data.append(line)
|
|
return Dataset.from_list(data)
|