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>
67 lines
2.0 KiB
Python
67 lines
2.0 KiB
Python
from opencompass.openicl.icl_prompt_template import PromptTemplate
|
|
from opencompass.openicl.icl_retriever import ZeroRetriever
|
|
from opencompass.openicl.icl_inferencer import PPLInferencer
|
|
from opencompass.openicl.icl_evaluator import AccEvaluator
|
|
from opencompass.datasets import OBQADataset
|
|
|
|
_input_columns = [
|
|
['question_stem', 'A', 'B', 'C', 'D'],
|
|
['question_stem', 'A', 'B', 'C', 'D', 'fact1'],
|
|
]
|
|
_template = [
|
|
{
|
|
ans: dict(
|
|
round=[
|
|
dict(
|
|
role='HUMAN',
|
|
prompt=
|
|
'Question: {question_stem}\nA. {A}\nB. {B}\nC. {C}\nD. {D}\nAnswer:'
|
|
),
|
|
dict(role='BOT', prompt=ans),
|
|
], )
|
|
for ans in ['A', 'B', 'C', 'D']
|
|
},
|
|
{
|
|
ans: dict(
|
|
round=[
|
|
dict(
|
|
role='HUMAN',
|
|
prompt=
|
|
'Given the fact: {fact1}\nQuestion: {question_stem}\nA. {A}\nB. {B}\nC. {C}\nD. {D}\nAnswer:'
|
|
),
|
|
dict(role='BOT', prompt=ans),
|
|
], )
|
|
for ans in ['A', 'B', 'C', 'D']
|
|
}
|
|
]
|
|
|
|
obqa_datasets = [
|
|
dict(
|
|
abbr='openbookqa',
|
|
type=OBQADataset,
|
|
path='opencompass/openbookqa_test',
|
|
name='main',
|
|
),
|
|
dict(
|
|
abbr='openbookqa_fact',
|
|
type=OBQADataset,
|
|
path='opencompass/openbookqa_fact',
|
|
name='additional',
|
|
),
|
|
]
|
|
for _i in range(2):
|
|
obqa_reader_cfg = dict(
|
|
input_columns=_input_columns[_i], output_column='answerKey')
|
|
obqa_infer_cfg = dict(
|
|
prompt_template=dict(
|
|
type=PromptTemplate,
|
|
template=_template[_i]),
|
|
retriever=dict(type=ZeroRetriever),
|
|
inferencer=dict(type=PPLInferencer),
|
|
)
|
|
obqa_eval_cfg = dict(evaluator=dict(type=AccEvaluator), )
|
|
|
|
obqa_datasets[_i]['reader_cfg'] = obqa_reader_cfg
|
|
obqa_datasets[_i]['infer_cfg'] = obqa_infer_cfg
|
|
obqa_datasets[_i]['eval_cfg'] = obqa_eval_cfg
|