2024-03-04 14:42:36 +08:00
|
|
|
from opencompass.openicl.icl_prompt_template import PromptTemplate
|
|
|
|
from opencompass.openicl.icl_retriever import ZeroRetriever, FixKRetriever
|
|
|
|
from opencompass.openicl.icl_inferencer import GenInferencer
|
[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 TriviaQADatasetV2, TriviaQAEvaluator
|
2024-03-04 14:42:36 +08:00
|
|
|
|
|
|
|
|
|
|
|
triviaqa_datasets = []
|
|
|
|
for k in [1]:
|
|
|
|
triviaqa_reader_cfg = dict(
|
|
|
|
input_columns=['question'], output_column='answer', train_split='train', test_split='validation')
|
|
|
|
|
|
|
|
if k == 0:
|
|
|
|
triviaqa_infer_cfg = dict(
|
|
|
|
prompt_template=dict(
|
|
|
|
type=PromptTemplate,
|
|
|
|
template=dict(
|
|
|
|
round=[
|
|
|
|
dict(role='HUMAN', prompt='Q: {question}'),
|
|
|
|
dict(role='BOT', prompt='A:'),
|
|
|
|
]
|
|
|
|
)
|
|
|
|
),
|
|
|
|
retriever=dict(type=ZeroRetriever),
|
|
|
|
inferencer=dict(type=GenInferencer, max_out_len=50)
|
|
|
|
)
|
|
|
|
else:
|
|
|
|
triviaqa_infer_cfg = dict(
|
|
|
|
ice_template=dict(
|
|
|
|
type=PromptTemplate,
|
|
|
|
template=dict(
|
|
|
|
round=[
|
|
|
|
dict(role='HUMAN', prompt='Q: {question}'),
|
|
|
|
dict(role='BOT', prompt='A: {answer}.\n'),
|
|
|
|
]
|
|
|
|
),
|
|
|
|
),
|
|
|
|
prompt_template=dict(
|
|
|
|
type=PromptTemplate,
|
|
|
|
template=dict(
|
2024-05-14 15:35:58 +08:00
|
|
|
begin='</E>',
|
2024-03-04 14:42:36 +08:00
|
|
|
round=[
|
|
|
|
dict(role='HUMAN', prompt='Q: {question}'),
|
|
|
|
dict(role='BOT', prompt='A:'),
|
|
|
|
]
|
|
|
|
),
|
2024-05-14 15:35:58 +08:00
|
|
|
ice_token='</E>',
|
2024-03-04 14:42:36 +08:00
|
|
|
),
|
|
|
|
retriever=dict(type=FixKRetriever, fix_id_list=list(range(k))),
|
2024-05-14 15:35:58 +08:00
|
|
|
inferencer=dict(type=GenInferencer, max_out_len=50, stopping_criteria=['Q:', '\n']),
|
2024-03-04 14:42:36 +08:00
|
|
|
)
|
|
|
|
|
2024-05-14 15:35:58 +08:00
|
|
|
triviaqa_eval_cfg = dict(evaluator=dict(type=TriviaQAEvaluator), pred_role='BOT')
|
2024-03-04 14:42:36 +08:00
|
|
|
|
|
|
|
triviaqa_datasets.append(
|
|
|
|
dict(
|
[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=TriviaQADatasetV2,
|
2024-03-04 14:42:36 +08:00
|
|
|
abbr=f'triviaqa_wiki_{k}shot',
|
[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
|
|
|
path='opencompass/trivia_qa',
|
2024-03-04 14:42:36 +08:00
|
|
|
reader_cfg=triviaqa_reader_cfg,
|
|
|
|
infer_cfg=triviaqa_infer_cfg,
|
|
|
|
eval_cfg=triviaqa_eval_cfg)
|
|
|
|
)
|