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>
81 lines
3.2 KiB
Python
81 lines
3.2 KiB
Python
import json
|
|
import os
|
|
from os import environ
|
|
|
|
from datasets import Dataset, DatasetDict
|
|
|
|
from opencompass.registry import LOAD_DATASET
|
|
from opencompass.utils import get_data_path
|
|
|
|
from .base import BaseDataset
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class StoryClozeDataset(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path, lang):
|
|
path = get_data_path(path)
|
|
dataset_list = []
|
|
for split in ['train', 'eval']:
|
|
if environ.get('DATASET_SOURCE') == 'ModelScope':
|
|
from modelscope import MsDataset
|
|
ms_dataset = MsDataset.load(path,
|
|
subset_name=lang,
|
|
split=split)
|
|
for line in ms_dataset:
|
|
line['context'] = ' '.join([
|
|
line['input_sentence_1'], line['input_sentence_2'],
|
|
line['input_sentence_3'], line['input_sentence_4']
|
|
])
|
|
dataset_list.append(line)
|
|
else:
|
|
split_path = os.path.join(path, f'{lang}_{split}.jsonl')
|
|
with open(split_path, 'r', encoding='utf-8') as f:
|
|
for line in f:
|
|
line = json.loads(line)
|
|
line['context'] = ' '.join([
|
|
line['input_sentence_1'], line['input_sentence_2'],
|
|
line['input_sentence_3'], line['input_sentence_4']
|
|
])
|
|
dataset_list.append(line)
|
|
dataset_list = Dataset.from_list(dataset_list)
|
|
return DatasetDict({'test': dataset_list})
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class StoryClozeDatasetV2(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path, lang):
|
|
path = get_data_path(path)
|
|
dataset_list = []
|
|
for split in ['train', 'eval']:
|
|
if environ.get('DATASET_SOURCE') == 'ModelScope':
|
|
from modelscope import MsDataset
|
|
ms_dataset = MsDataset.load(path,
|
|
subset_name=lang,
|
|
split=split)
|
|
for line in ms_dataset:
|
|
line['context'] = ' '.join([
|
|
line['input_sentence_1'], line['input_sentence_2'],
|
|
line['input_sentence_3'], line['input_sentence_4']
|
|
])
|
|
line['answer_right_ending'] = ' AB'[
|
|
line['answer_right_ending']]
|
|
dataset_list.append(line)
|
|
else:
|
|
split_path = os.path.join(path, f'{lang}_{split}.jsonl')
|
|
with open(split_path, 'r', encoding='utf-8') as f:
|
|
for line in f:
|
|
line = json.loads(line)
|
|
line['context'] = ' '.join([
|
|
line['input_sentence_1'], line['input_sentence_2'],
|
|
line['input_sentence_3'], line['input_sentence_4']
|
|
])
|
|
line['answer_right_ending'] = ' AB'[
|
|
line['answer_right_ending']]
|
|
dataset_list.append(line)
|
|
dataset_list = Dataset.from_list(dataset_list)
|
|
return dataset_list
|