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>
36 lines
1.2 KiB
Python
36 lines
1.2 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 AccContaminationEvaluator
|
|
from opencompass.datasets import HellaswagDatasetClean as HellaswagDataset
|
|
|
|
hellaswag_reader_cfg = dict(
|
|
input_columns=['ctx', 'A', 'B', 'C', 'D'],
|
|
output_column='label')
|
|
|
|
hellaswag_infer_cfg = dict(
|
|
prompt_template=dict(
|
|
type=PromptTemplate,
|
|
template={
|
|
i: dict(round=[
|
|
dict(role='HUMAN', prompt='{ctx}'),
|
|
dict(role='BOT', prompt=f"{{{chr(ord('A') + i)}}}"),
|
|
])
|
|
for i in range(4)
|
|
}),
|
|
retriever=dict(type=ZeroRetriever),
|
|
inferencer=dict(type=PPLInferencer))
|
|
|
|
hellaswag_eval_cfg = dict(evaluator=dict(type=AccContaminationEvaluator),
|
|
analyze_contamination=True)
|
|
|
|
hellaswag_datasets = [
|
|
dict(
|
|
abbr='hellaswag',
|
|
type=HellaswagDataset,
|
|
path='opencompass/hellaswag',
|
|
reader_cfg=hellaswag_reader_cfg,
|
|
infer_cfg=hellaswag_infer_cfg,
|
|
eval_cfg=hellaswag_eval_cfg)
|
|
]
|