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>
53 lines
1.3 KiB
Python
53 lines
1.3 KiB
Python
import json
|
|
import os.path as osp
|
|
import re
|
|
|
|
from datasets import 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 ScibenchDataset(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path: str, name: str):
|
|
path = get_data_path(path, local_mode=True)
|
|
train_data = []
|
|
|
|
filename = osp.join(path, f'{name}.json')
|
|
with open(filename, 'r') as infile:
|
|
raw_data = json.load(infile)
|
|
|
|
for entry in raw_data:
|
|
train_data.append({
|
|
'question': entry['problem_text'].strip(),
|
|
'answer': entry['answer_number'].strip()
|
|
})
|
|
|
|
dataset = Dataset.from_list(train_data)
|
|
return dataset
|
|
|
|
|
|
@TEXT_POSTPROCESSORS.register_module('scibench')
|
|
def scibench_postprocess(text: str) -> str:
|
|
ans = text
|
|
ans_line = ans.split('answer is')
|
|
if len(ans_line) != 1:
|
|
ans = ans_line[1].strip()
|
|
|
|
match = re.search(r'\\boxed\{(.+?)\}', ans)
|
|
if match:
|
|
extracted_content = match.group(1)
|
|
return extracted_content
|
|
|
|
output = re.sub(r'(\d),(\d)', r'\1\2', ans)
|
|
numbers = re.findall(r'-?\d*\.?\d+|\d+', output)
|
|
if numbers:
|
|
return numbers[-1]
|
|
|
|
return ans
|