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>
49 lines
1.4 KiB
Python
49 lines
1.4 KiB
Python
import json
|
|
|
|
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 CHIDDataset(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)
|
|
|
|
def preprocess(example):
|
|
content = example['content']
|
|
for i, c in enumerate(example['candidates']):
|
|
example[f'content{i}'] = content.replace('#idiom#', c)
|
|
return example
|
|
|
|
dataset = dataset.map(preprocess)
|
|
return dataset
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class CHIDDatasetV2(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path):
|
|
path = get_data_path(path, local_mode=True)
|
|
data = []
|
|
with open(path, 'r', encoding='utf-8') as f:
|
|
for line in f:
|
|
line = json.loads(line)
|
|
item = {}
|
|
item['content'] = line['content'].replace('#idiom#', '______')
|
|
for i, c in enumerate(line['candidates']):
|
|
item[chr(ord('A') + i)] = c
|
|
item['answer'] = 'ABCDEFG'[line['answer']]
|
|
data.append(item)
|
|
return Dataset.from_list(data)
|