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>
100 lines
3.3 KiB
Python
100 lines
3.3 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.openicl.icl_evaluator import AccEvaluator
|
|
from opencompass.datasets import BBHDataset, BBHEvaluator, bbh_mcq_postprocess, BBHEvaluator_mcq
|
|
|
|
bbh_reader_cfg = dict(input_columns=['input'], output_column='target')
|
|
|
|
bbh_multiple_choice_sets = [
|
|
'temporal_sequences',
|
|
'disambiguation_qa',
|
|
'date_understanding',
|
|
'tracking_shuffled_objects_three_objects',
|
|
'penguins_in_a_table',
|
|
'geometric_shapes',
|
|
'snarks',
|
|
'ruin_names',
|
|
'tracking_shuffled_objects_seven_objects',
|
|
'tracking_shuffled_objects_five_objects',
|
|
'logical_deduction_three_objects',
|
|
'hyperbaton',
|
|
'logical_deduction_five_objects',
|
|
'logical_deduction_seven_objects',
|
|
'movie_recommendation',
|
|
'salient_translation_error_detection',
|
|
'reasoning_about_colored_objects',
|
|
]
|
|
bbh_free_form_sets = [
|
|
'multistep_arithmetic_two',
|
|
'navigate',
|
|
'dyck_languages',
|
|
'word_sorting',
|
|
'sports_understanding',
|
|
'boolean_expressions',
|
|
'object_counting',
|
|
'formal_fallacies',
|
|
'causal_judgement',
|
|
'web_of_lies',
|
|
]
|
|
|
|
bbh_datasets = []
|
|
for _name in bbh_multiple_choice_sets:
|
|
with open(os.path.join(os.path.dirname(__file__), 'lib_prompt', f'{_name}.txt'), 'r') as f:
|
|
_hint = f.read()
|
|
bbh_infer_cfg = dict(
|
|
prompt_template=dict(
|
|
type=PromptTemplate,
|
|
template=dict(round=[
|
|
dict(
|
|
role='HUMAN',
|
|
prompt=
|
|
f'Follow the given examples and answer the question.\n{_hint}\n\nQ: {{input}}\nA: '
|
|
)
|
|
])),
|
|
retriever=dict(type=ZeroRetriever),
|
|
inferencer=dict(type=GenInferencer, max_out_len=512))
|
|
bbh_eval_cfg = dict(
|
|
evaluator=dict(type=BBHEvaluator_mcq),
|
|
pred_role='BOT',
|
|
pred_postprocessor=dict(type=bbh_mcq_postprocess),
|
|
dataset_postprocessor=dict(type=bbh_mcq_postprocess))
|
|
|
|
bbh_datasets.append(
|
|
dict(
|
|
type=BBHDataset,
|
|
path='opencompass/bbh',
|
|
name=_name,
|
|
abbr='bbh-' + _name,
|
|
reader_cfg=bbh_reader_cfg,
|
|
infer_cfg=bbh_infer_cfg.copy(),
|
|
eval_cfg=bbh_eval_cfg.copy()))
|
|
|
|
for _name in bbh_free_form_sets:
|
|
with open(os.path.join(os.path.dirname(__file__), 'lib_prompt', f'{_name}.txt'), 'r') as f:
|
|
_hint = f.read()
|
|
bbh_infer_cfg = dict(
|
|
prompt_template=dict(
|
|
type=PromptTemplate,
|
|
template=dict(round=[
|
|
dict(
|
|
role='HUMAN',
|
|
prompt=
|
|
f'Follow the given examples and answer the question.\n{_hint}\n\nQ: {{input}}\nA: '
|
|
)
|
|
])),
|
|
retriever=dict(type=ZeroRetriever),
|
|
inferencer=dict(type=GenInferencer, max_out_len=512))
|
|
bbh_eval_cfg = dict(evaluator=dict(type=BBHEvaluator), pred_role='BOT')
|
|
|
|
bbh_datasets.append(
|
|
dict(
|
|
type=BBHDataset,
|
|
path='opencompass/bbh',
|
|
name=_name,
|
|
abbr='bbh-' + _name,
|
|
reader_cfg=bbh_reader_cfg,
|
|
infer_cfg=bbh_infer_cfg.copy(),
|
|
eval_cfg=bbh_eval_cfg.copy()))
|