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>
58 lines
1.6 KiB
Python
58 lines
1.6 KiB
Python
from opencompass.openicl.icl_prompt_template import PromptTemplate
|
|
from opencompass.openicl.icl_retriever import ZeroRetriever
|
|
from opencompass.openicl.icl_inferencer import PPLOnlyInferencer
|
|
from opencompass.openicl.icl_evaluator import AveragePPLEvaluator
|
|
from opencompass.datasets import SanitizedMBPPDataset, JsonlDataset
|
|
|
|
mbpp_datasets = []
|
|
|
|
mbpp_infer_cfg = dict(
|
|
prompt_template=dict(type=PromptTemplate, template='{text}\n{code}'),
|
|
retriever=dict(type=ZeroRetriever),
|
|
inferencer=dict(type=PPLOnlyInferencer),
|
|
)
|
|
|
|
mbpp_eval_cfg = dict(evaluator=dict(type=AveragePPLEvaluator))
|
|
|
|
for split in ['train', 'test']:
|
|
mbpp_reader_cfg = dict(
|
|
input_columns=['text', 'code'],
|
|
output_column=None,
|
|
train_split=split,
|
|
test_split=split,
|
|
)
|
|
mbpp_datasets.append(
|
|
dict(
|
|
abbr=f'mbpp-{split}-ppl',
|
|
type=SanitizedMBPPDataset,
|
|
path='opencompass/sanitized_mbpp',
|
|
reader_cfg=mbpp_reader_cfg,
|
|
infer_cfg=mbpp_infer_cfg,
|
|
eval_cfg=mbpp_eval_cfg)
|
|
)
|
|
|
|
|
|
mbpp_infer_cfg = dict(
|
|
prompt_template=dict(type=PromptTemplate, template='{text}'),
|
|
retriever=dict(type=ZeroRetriever),
|
|
inferencer=dict(type=PPLOnlyInferencer),
|
|
)
|
|
|
|
mbpp_eval_cfg = dict(evaluator=dict(type=AveragePPLEvaluator))
|
|
|
|
mbpp_reader_cfg = dict(
|
|
input_columns=['text'],
|
|
output_column=None,
|
|
)
|
|
|
|
mbpp_datasets.append(
|
|
dict(
|
|
abbr=f'mbpp-ref-ppl',
|
|
type=JsonlDataset,
|
|
path='/mnt/petrelfs/zhoufengzhe/repos/cscripts/mock-datas/mock_mbpp_20240113.jsonl',
|
|
reader_cfg=mbpp_reader_cfg,
|
|
infer_cfg=mbpp_infer_cfg,
|
|
eval_cfg=mbpp_eval_cfg
|
|
)
|
|
)
|