2023-07-05 10:33:12 +08:00
|
|
|
|
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
|
[Feature] Support ModelScope datasets (#1289)
* 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>
2024-07-29 13:48:32 +08:00
|
|
|
|
from opencompass.datasets import CMNLIDatasetV2
|
2023-07-06 12:27:41 +08:00
|
|
|
|
from opencompass.utils.text_postprocessors import first_capital_postprocess
|
2023-07-05 10:33:12 +08:00
|
|
|
|
|
|
|
|
|
ocnli_reader_cfg = dict(
|
2024-05-14 15:35:58 +08:00
|
|
|
|
input_columns=['sentence1', 'sentence2'],
|
|
|
|
|
output_column='label',
|
2023-07-05 10:33:12 +08:00
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
# TODO: two prompt templates for ocnli
|
|
|
|
|
ocnli_infer_cfg = dict(
|
|
|
|
|
prompt_template=dict(
|
|
|
|
|
type=PromptTemplate,
|
|
|
|
|
template=dict(round=[
|
|
|
|
|
dict(
|
2024-05-14 15:35:58 +08:00
|
|
|
|
role='HUMAN',
|
2023-07-05 10:33:12 +08:00
|
|
|
|
prompt=
|
2024-05-14 15:35:58 +08:00
|
|
|
|
'阅读文章:{sentence1}\n根据上文,回答如下问题:{sentence2}\nA. 对\nB. 错\nC. 可能\n请从“A”,“B”,“C”中进行选择。\n答:'
|
2023-07-05 10:33:12 +08:00
|
|
|
|
),
|
|
|
|
|
]),
|
|
|
|
|
),
|
|
|
|
|
retriever=dict(type=ZeroRetriever),
|
|
|
|
|
inferencer=dict(type=GenInferencer),
|
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
ocnli_eval_cfg = dict(
|
|
|
|
|
evaluator=dict(type=AccEvaluator),
|
2024-05-14 15:35:58 +08:00
|
|
|
|
pred_role='BOT',
|
2023-07-06 12:27:41 +08:00
|
|
|
|
pred_postprocessor=dict(type=first_capital_postprocess),
|
2023-07-05 10:33:12 +08:00
|
|
|
|
)
|
|
|
|
|
|
|
|
|
|
ocnli_datasets = [
|
|
|
|
|
dict(
|
2024-05-14 15:35:58 +08:00
|
|
|
|
abbr='ocnli',
|
[Feature] Support ModelScope datasets (#1289)
* 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>
2024-07-29 13:48:32 +08:00
|
|
|
|
type=CMNLIDatasetV2, # ocnli share the same format with cmnli
|
|
|
|
|
path='opencompass/OCNLI-dev',
|
2023-07-05 10:33:12 +08:00
|
|
|
|
reader_cfg=ocnli_reader_cfg,
|
|
|
|
|
infer_cfg=ocnli_infer_cfg,
|
|
|
|
|
eval_cfg=ocnli_eval_cfg,
|
|
|
|
|
)
|
|
|
|
|
]
|