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>
50 lines
1.4 KiB
Python
50 lines
1.4 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 WSCDatasetV3
|
|
|
|
WSC_reader_cfg = dict(
|
|
input_columns=['span1', 'span2', 'text'],
|
|
output_column='label',
|
|
)
|
|
|
|
WSC_infer_cfg = dict(
|
|
prompt_template=dict(
|
|
type=PromptTemplate,
|
|
template={
|
|
'A':
|
|
dict(round=[
|
|
dict(
|
|
role='HUMAN',
|
|
prompt='Passage: {text}\nDoes the pronoun # {span2} # refer to * {span1} *?\nA. Yes\nB. No\nAnswer: '
|
|
),
|
|
dict(role='BOT', prompt='A'),
|
|
]),
|
|
'B':
|
|
dict(round=[
|
|
dict(
|
|
role='HUMAN',
|
|
prompt='Passage: {text}\nDoes the pronoun # {span2} # refer to * {span1} *?\nA. Yes\nB. No\nAnswer: '
|
|
),
|
|
dict(role='BOT', prompt='B'),
|
|
]),
|
|
},
|
|
),
|
|
retriever=dict(type=ZeroRetriever),
|
|
inferencer=dict(type=PPLInferencer),
|
|
)
|
|
|
|
WSC_eval_cfg = dict(evaluator=dict(type=AccEvaluator), )
|
|
|
|
WSC_datasets = [
|
|
dict(
|
|
abbr='WSC',
|
|
type=WSCDatasetV3,
|
|
path='./data/SuperGLUE/WSC/val.jsonl',
|
|
reader_cfg=WSC_reader_cfg,
|
|
infer_cfg=WSC_infer_cfg,
|
|
eval_cfg=WSC_eval_cfg,
|
|
)
|
|
]
|