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>
125 lines
3.6 KiB
Python
125 lines
3.6 KiB
Python
from opencompass.openicl.icl_prompt_template import PromptTemplate
|
|
from opencompass.openicl.icl_retriever import FixKRetriever
|
|
from opencompass.openicl.icl_inferencer import GenInferencer
|
|
from opencompass.openicl.icl_evaluator import AccEvaluator
|
|
from opencompass.datasets import MMLUDataset
|
|
from opencompass.utils.text_postprocessors import first_capital_postprocess
|
|
|
|
# None of the mmlu dataset in huggingface is correctly parsed, so we use our own dataset reader
|
|
# Please download the dataset from https://people.eecs.berkeley.edu/~hendrycks/data.tar
|
|
|
|
mmlu_reader_cfg = dict(
|
|
input_columns=['input', 'A', 'B', 'C', 'D'],
|
|
output_column='target',
|
|
train_split='dev')
|
|
|
|
mmlu_prompt_template = dict(
|
|
type='PromptTemplate',
|
|
template=None,
|
|
ice_token='</E>')
|
|
|
|
mmlu_infer_cfg = dict(
|
|
ice_template=dict(
|
|
type=PromptTemplate,
|
|
template=dict(round=[
|
|
dict(
|
|
role='HUMAN',
|
|
prompt='{input}\nA. {A}\nB. {B}\nC. {C}\nD. {D}\nAnswer: '
|
|
),
|
|
dict(role='BOT', prompt='{target}\n')
|
|
])),
|
|
prompt_template=mmlu_prompt_template,
|
|
retriever=dict(type=FixKRetriever, fix_id_list=[0, 1, 2, 3, 4]),
|
|
inferencer=dict(type=GenInferencer))
|
|
|
|
mmlu_eval_cfg = dict(
|
|
evaluator=dict(type=AccEvaluator),
|
|
pred_postprocessor=dict(type=first_capital_postprocess))
|
|
|
|
mmlu_all_sets = [
|
|
'college_biology',
|
|
'college_chemistry',
|
|
'college_computer_science',
|
|
'college_mathematics',
|
|
'college_physics',
|
|
'electrical_engineering',
|
|
'astronomy',
|
|
'anatomy',
|
|
'abstract_algebra',
|
|
'machine_learning',
|
|
'clinical_knowledge',
|
|
'global_facts',
|
|
'management',
|
|
'nutrition',
|
|
'marketing',
|
|
'professional_accounting',
|
|
'high_school_geography',
|
|
'international_law',
|
|
'moral_scenarios',
|
|
'computer_security',
|
|
'high_school_microeconomics',
|
|
'professional_law',
|
|
'medical_genetics',
|
|
'professional_psychology',
|
|
'jurisprudence',
|
|
'world_religions',
|
|
'philosophy',
|
|
'virology',
|
|
'high_school_chemistry',
|
|
'public_relations',
|
|
'high_school_macroeconomics',
|
|
'human_sexuality',
|
|
'elementary_mathematics',
|
|
'high_school_physics',
|
|
'high_school_computer_science',
|
|
'high_school_european_history',
|
|
'business_ethics',
|
|
'moral_disputes',
|
|
'high_school_statistics',
|
|
'miscellaneous',
|
|
'formal_logic',
|
|
'high_school_government_and_politics',
|
|
'prehistory',
|
|
'security_studies',
|
|
'high_school_biology',
|
|
'logical_fallacies',
|
|
'high_school_world_history',
|
|
'professional_medicine',
|
|
'high_school_mathematics',
|
|
'college_medicine',
|
|
'high_school_us_history',
|
|
'sociology',
|
|
'econometrics',
|
|
'high_school_psychology',
|
|
'human_aging',
|
|
'us_foreign_policy',
|
|
'conceptual_physics',
|
|
]
|
|
|
|
mmlu_datasets = []
|
|
for _name in mmlu_all_sets:
|
|
mmlu_datasets.append(
|
|
dict(
|
|
abbr=f'lukaemon_mmlu_{_name}',
|
|
type=MMLUDataset,
|
|
path='opencompass/mmlu',
|
|
name=_name,
|
|
reader_cfg=mmlu_reader_cfg,
|
|
infer_cfg=mmlu_infer_cfg.copy(),
|
|
eval_cfg=mmlu_eval_cfg))
|
|
|
|
mmlu_datasets[-1]['infer_cfg'][
|
|
'prompt_template'] = mmlu_prompt_template.copy()
|
|
mmlu_datasets[-1]['infer_cfg']['prompt_template']['template'] = \
|
|
dict(
|
|
begin=[
|
|
dict(role='SYSTEM', fallback_role='HUMAN', prompt=f'The following are multiple choice questions (with answers) about {_name.replace("_", " ")}.'),
|
|
'</E>',
|
|
],
|
|
round=[
|
|
dict(role='HUMAN', prompt='{input}\nA. {A}\nB. {B}\nC. {C}\nD. {D}\nAnswer: '),
|
|
]
|
|
)
|
|
|
|
del _name
|