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>
61 lines
1.9 KiB
Python
61 lines
1.9 KiB
Python
import json
|
|
import os.path as osp
|
|
from typing import Dict, Optional
|
|
|
|
import mmengine
|
|
from datasets import Dataset, DatasetDict
|
|
|
|
from opencompass.registry import TEXT_POSTPROCESSORS
|
|
from opencompass.utils import get_data_path
|
|
|
|
from ..base import BaseDataset
|
|
|
|
|
|
class TEvalDataset(BaseDataset):
|
|
|
|
def __init__(self, reader_cfg: Optional[Dict] = {}, **kwargs):
|
|
super().__init__(reader_cfg=reader_cfg, **kwargs)
|
|
|
|
def load(self, path: str, name: str):
|
|
path = get_data_path(path, local_mode=True)
|
|
|
|
dataset = DatasetDict()
|
|
data = mmengine.load(osp.join(path, f'{name}.json'))
|
|
raw_data = []
|
|
for i in data.keys():
|
|
origin_prompt = data[i]['origin_prompt']
|
|
if isinstance(origin_prompt, str):
|
|
origin_prompt = json.loads(origin_prompt)
|
|
# Aligning the default roles of opencompass
|
|
prompt = origin_prompt + [
|
|
dict(role='assistant',
|
|
content=str(data[i].get('ground_truth')))
|
|
]
|
|
raw_data.append({
|
|
'prompt': prompt,
|
|
'ground_truth': json.dumps(data[i])
|
|
})
|
|
dataset['test'] = Dataset.from_list(raw_data)
|
|
dataset['train'] = Dataset.from_list(raw_data)
|
|
return dataset
|
|
|
|
|
|
|
|
|
|
@TEXT_POSTPROCESSORS.register_module('teval')
|
|
def teval_postprocess(text: str) -> str:
|
|
if isinstance(text, str):
|
|
text = text.split('<eoa>')[0]
|
|
text = text.split('<TOKENS_UNUSED_1>')[0]
|
|
text = text.split('<|im_end|>')[0]
|
|
text = text.split('\nuser')[0]
|
|
text = text.split('\nUSER')[0]
|
|
text = text.split('[INST]')[0]
|
|
text = text.strip()
|
|
if text.startswith('```json'):
|
|
text = text[len('```json'):]
|
|
text = text.strip('`').strip()
|
|
if text[:2] == '{{' and text[-2:] == '}}':
|
|
text = text[1:-1]
|
|
return str(text)
|