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>
43 lines
1.5 KiB
Python
43 lines
1.5 KiB
Python
import os
|
|
from opencompass.openicl.icl_prompt_template import PromptTemplate
|
|
from opencompass.openicl.icl_retriever import ZeroRetriever
|
|
from opencompass.openicl.icl_inferencer import GenInferencer
|
|
from opencompass.datasets import GaokaoBenchDataset
|
|
from mmengine.config import read_base
|
|
|
|
with read_base():
|
|
from .GaokaoBench_prompts import MCQ_prompts, FBQ_prompts
|
|
|
|
GaokaoBench_datasets = []
|
|
for folder, prompts in [
|
|
('Multiple-choice_Questions', MCQ_prompts),
|
|
('Fill-in-the-blank_Questions', FBQ_prompts),
|
|
]:
|
|
for p in prompts:
|
|
reader_cfg = {
|
|
'input_columns': ['question'],
|
|
'output_column': 'answer',
|
|
}
|
|
infer_cfg = {
|
|
'prompt_template': {
|
|
'type': PromptTemplate,
|
|
'template': p['prefix_prompt'] + '{question}',
|
|
},
|
|
'retriever': {'type': ZeroRetriever},
|
|
'inferencer': {'type': GenInferencer, 'max_out_len': 1024},
|
|
}
|
|
eval_cfg = {
|
|
'evaluator': {'type': 'GaokaoBenchEvaluator' + '_' + p['type']},
|
|
'pred_role': 'BOT',
|
|
}
|
|
dataset = {
|
|
'type': GaokaoBenchDataset,
|
|
'abbr': 'GaokaoBench_' + p['keyword'],
|
|
'path': os.path.join('data', 'GAOKAO-BENCH', 'data', folder, p['keyword'] + '.json'),
|
|
'name': p['keyword'],
|
|
'reader_cfg': reader_cfg,
|
|
'infer_cfg': infer_cfg,
|
|
'eval_cfg': eval_cfg,
|
|
}
|
|
GaokaoBench_datasets.append(dataset)
|