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>
60 lines
1.7 KiB
Python
60 lines
1.7 KiB
Python
# flake8: noqa: E501
|
|
import json
|
|
import os.path as osp
|
|
import re
|
|
from typing import Optional
|
|
|
|
from datasets import Dataset, DatasetDict
|
|
|
|
from opencompass.registry import LOAD_DATASET
|
|
from opencompass.utils import get_data_path
|
|
|
|
from .subjective.subjective_cmp import SubjectiveCmpDataset
|
|
|
|
|
|
class Config:
|
|
|
|
def __init__(self, flames_config_path, flames_bench_config_name) -> None:
|
|
config_file_path = osp.join(flames_config_path,
|
|
flames_bench_config_name)
|
|
with open(config_file_path, 'r') as config_file:
|
|
self.config = ''.join(config_file.readlines())
|
|
config_file.close()
|
|
|
|
|
|
def prompt_construct(sample, config: Config):
|
|
dimensions = config.config
|
|
base_prompt = '{dimensions}'\
|
|
'{question}\n' \
|
|
'回答: '
|
|
prompt = base_prompt.format(dimensions=dimensions,
|
|
question=sample['prompt'])
|
|
|
|
return prompt
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class FlamesDataset(SubjectiveCmpDataset):
|
|
|
|
def load(
|
|
self,
|
|
path: str,
|
|
name: str,
|
|
):
|
|
path = get_data_path(path, local_mode=True)
|
|
config = Config(path, f'{name}_config.txt')
|
|
|
|
dataset = []
|
|
with open(osp.join(path, f'{name}.json')) as f:
|
|
dataset = json.load(f)
|
|
flames_dataset = []
|
|
for ins in dataset:
|
|
ins['instruction'] = prompt_construct(ins, config)
|
|
ins['judge'] = {
|
|
'dimension': ins['dimension'],
|
|
'subcomponent': ins['subcomponent']
|
|
}
|
|
flames_dataset.append(ins)
|
|
flames_dataset = Dataset.from_list(flames_dataset)
|
|
return flames_dataset
|