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>
55 lines
1.8 KiB
Python
55 lines
1.8 KiB
Python
import json
|
|
from os import environ
|
|
|
|
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 XsumDataset(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path: str):
|
|
path = get_data_path(path)
|
|
if environ.get('DATASET_SOURCE') == 'ModelScope':
|
|
from modelscope import MsDataset
|
|
ms_dataset = MsDataset.load(path, split='validation')
|
|
rows = []
|
|
for i, line in enumerate(ms_dataset):
|
|
if i == 1000:
|
|
break
|
|
dialogue = line['document']
|
|
summary = line['summary']
|
|
if not dialogue or not summary:
|
|
continue
|
|
rows.append({'dialogue': dialogue, 'summary': summary})
|
|
dataset = Dataset.from_list(rows)
|
|
else:
|
|
with open(path, 'r', errors='ignore') as in_f:
|
|
rows = []
|
|
for i, line in enumerate(in_f):
|
|
if i == 1000:
|
|
break
|
|
sample = json.loads(line.strip())
|
|
dialogue = sample['dialogue']
|
|
summary = sample['summary']
|
|
if isinstance(dialogue, float) or isinstance(
|
|
summary, float):
|
|
continue
|
|
rows.append({'dialogue': dialogue, 'summary': summary})
|
|
dataset = Dataset.from_dict({
|
|
'dialogue': [row['dialogue'] for row in rows],
|
|
'summary': [row['summary'] for row in rows]
|
|
})
|
|
return dataset
|
|
|
|
|
|
@TEXT_POSTPROCESSORS.register_module('Xsum')
|
|
def Xsum_postprocess(text: str) -> str:
|
|
text = text.strip().split('\n')[0].strip()
|
|
return text
|