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>
33 lines
1.1 KiB
Python
33 lines
1.1 KiB
Python
from datasets import Dataset, load_dataset
|
|
|
|
from opencompass.registry import LOAD_DATASET
|
|
from opencompass.utils import get_data_path
|
|
|
|
from ..base import BaseDataset
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class LEvalPatentSummDataset(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(**kwargs):
|
|
if 'data_files' in kwargs:
|
|
kwargs['data_files'] = get_data_path(kwargs['data_files'],
|
|
local_mode=True)
|
|
dataset = load_dataset(**kwargs)
|
|
split = 'test'
|
|
raw_data = []
|
|
for i in range(len(dataset[split])):
|
|
instructions = dataset[split]['instructions'][i]
|
|
outputs = dataset[split]['outputs'][i]
|
|
context = dataset[split]['input'][i]
|
|
for question, answer in zip(instructions, outputs):
|
|
raw_data.append({
|
|
'question': question,
|
|
'context': context,
|
|
'length': len(answer.split()),
|
|
'answer': answer
|
|
})
|
|
dataset[split] = Dataset.from_list(raw_data)
|
|
return dataset
|