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 json
|
|
import re
|
|
|
|
from datasets import Dataset
|
|
|
|
from opencompass.registry import LOAD_DATASET
|
|
from opencompass.utils import get_data_path
|
|
|
|
from .base import BaseDataset
|
|
|
|
|
|
def py150_post_process(code):
|
|
code = code.replace('<NUM_LIT>',
|
|
'0').replace('<STR_LIT>',
|
|
'').replace('<CHAR_LIT>', '')
|
|
pattern = re.compile(r'<(STR|NUM|CHAR)_LIT:(.*?)>', re.S)
|
|
lit_s = re.findall(pattern, code)
|
|
for lit in lit_s:
|
|
code = code.replace(f'<{lit[0]}_LIT:{lit[1]}>', lit[1])
|
|
code = json.loads(code)
|
|
code['input'] = code['input'].replace('<s>', '').split('<EOL>')
|
|
for code_line in code['input']:
|
|
code_line = code_line.strip()
|
|
code['input'] = '\n'.join(code['input'])
|
|
code.pop('id', None)
|
|
return code
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class Py150Dataset(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path):
|
|
path = get_data_path(path, local_mode=True)
|
|
lines = open(path, 'r').readlines()
|
|
rows = []
|
|
for line in lines:
|
|
row = py150_post_process(line)
|
|
rows.append(row)
|
|
return Dataset.from_list(rows)
|