OpenCompass/configs/datasets/agieval/agieval_gen_a0c741.py

86 lines
2.7 KiB
Python
Raw Normal View History

2023-07-04 21:34:55 +08:00
from opencompass.openicl.icl_prompt_template import PromptTemplate
from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_evaluator import AccEvaluator
from opencompass.datasets import AGIEvalDataset, AGIEvalEvaluator
from opencompass.utils.text_postprocessors import first_capital_postprocess
2023-07-04 21:34:55 +08:00
agieval_reader_cfg = dict(
input_columns=['problem_input'], output_column='label')
agieval_single_choice_sets = [
'gaokao-chinese',
'gaokao-english',
'gaokao-geography',
'gaokao-history',
'gaokao-biology',
'gaokao-chemistry',
'gaokao-mathqa',
'logiqa-zh',
'lsat-ar',
'lsat-lr',
'lsat-rc',
'logiqa-en',
'sat-math',
'sat-en',
'sat-en-without-passage',
'aqua-rat',
]
agieval_multiple_choices_sets = [
'gaokao-physics',
'jec-qa-kd',
'jec-qa-ca',
2023-07-04 21:34:55 +08:00
]
agieval_cloze_sets = ['gaokao-mathcloze', 'math']
agieval_datasets = []
for name in agieval_single_choice_sets:
agieval_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
round=[dict(role='HUMAN', prompt='{problem_input}')])),
retriever=dict(type=ZeroRetriever),
inferencer=dict(type=GenInferencer, labels=['A', 'B', 'C', 'D']))
agieval_eval_cfg = dict(
evaluator=dict(type=AccEvaluator),
pred_postprocessor=dict(type=first_capital_postprocess))
2023-07-04 21:34:55 +08:00
agieval_datasets.append(
dict(
type=AGIEvalDataset,
[Feature] Support ModelScope datasets (#1289) * 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>
2024-07-29 13:48:32 +08:00
path='opencompass/agieval',
2023-07-04 21:34:55 +08:00
name=name,
abbr='agieval-' + name,
setting_name='zero-shot',
reader_cfg=agieval_reader_cfg,
infer_cfg=agieval_infer_cfg.copy(),
eval_cfg=agieval_eval_cfg.copy()))
for name in agieval_multiple_choices_sets + agieval_cloze_sets:
2023-07-04 21:34:55 +08:00
agieval_infer_cfg = dict(
prompt_template=dict(
type=PromptTemplate,
template=dict(
2024-05-14 15:35:58 +08:00
round=[dict(role='HUMAN', prompt='{problem_input}')])),
2023-07-04 21:34:55 +08:00
retriever=dict(type=ZeroRetriever
), # retriver 不起作用,以输入参数为准 (zero-shot / few-shot)
inferencer=dict(type=GenInferencer))
agieval_eval_cfg = dict(
2024-05-14 15:35:58 +08:00
evaluator=dict(type=AGIEvalEvaluator), pred_role='BOT')
2023-07-04 21:34:55 +08:00
agieval_datasets.append(
dict(
type=AGIEvalDataset,
[Feature] Support ModelScope datasets (#1289) * 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>
2024-07-29 13:48:32 +08:00
path='opencompass/agieval',
2023-07-04 21:34:55 +08:00
name=name,
abbr='agieval-' + name,
setting_name='zero-shot',
reader_cfg=agieval_reader_cfg,
infer_cfg=agieval_infer_cfg.copy(),
eval_cfg=agieval_eval_cfg.copy()))
del name, agieval_infer_cfg, agieval_eval_cfg