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>
41 lines
1.1 KiB
Python
41 lines
1.1 KiB
Python
import re
|
|
|
|
from datasets import load_dataset
|
|
|
|
from opencompass.registry import LOAD_DATASET, TEXT_POSTPROCESSORS
|
|
from opencompass.utils import get_data_path
|
|
|
|
from ..base import BaseDataset
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class TheoremQADataset(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path: str):
|
|
path = get_data_path(path, local_mode=True)
|
|
return load_dataset('csv', data_files={'test': path})
|
|
|
|
|
|
@TEXT_POSTPROCESSORS.register_module('TheoremQA')
|
|
def TheoremQA_postprocess(text: str) -> str:
|
|
text = text.strip()
|
|
matches = re.findall(r'answer is ([^\s]+)', text)
|
|
if len(matches) == 0:
|
|
return text
|
|
else:
|
|
text = matches[0].strip().strip('.,?!\"\';:')
|
|
return text
|
|
|
|
|
|
def TheoremQA_postprocess_v2(text: str) -> str:
|
|
prediction = text.strip().strip('\n').split('\n')[-1]
|
|
tmp = ''
|
|
for entry in prediction.split(' ')[::-1]:
|
|
if entry == 'is' or entry == 'be' or entry == 'are' or entry.endswith(
|
|
':'):
|
|
break
|
|
tmp = entry + ' ' + tmp
|
|
prediction = tmp.strip().strip('.')
|
|
return prediction
|