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>
63 lines
2.2 KiB
Python
63 lines
2.2 KiB
Python
from opencompass.openicl.icl_prompt_template import PromptTemplate
|
|
from opencompass.openicl.icl_retriever import ZeroRetriever, FixKRetriever
|
|
from opencompass.openicl.icl_inferencer import GenInferencer
|
|
from opencompass.datasets import TriviaQADatasetV2, TriviaQAEvaluator
|
|
|
|
|
|
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(
|
|
begin='</E>',
|
|
round=[
|
|
dict(role='HUMAN', prompt='Q: {question}'),
|
|
dict(role='BOT', prompt='A:'),
|
|
]
|
|
),
|
|
ice_token='</E>',
|
|
),
|
|
retriever=dict(type=FixKRetriever, fix_id_list=list(range(k))),
|
|
inferencer=dict(type=GenInferencer, max_out_len=50, stopping_criteria=['Q:', '\n']),
|
|
)
|
|
|
|
triviaqa_eval_cfg = dict(evaluator=dict(type=TriviaQAEvaluator), pred_role='BOT')
|
|
|
|
triviaqa_datasets.append(
|
|
dict(
|
|
type=TriviaQADatasetV2,
|
|
abbr=f'triviaqa_wiki_{k}shot',
|
|
path='opencompass/trivia_qa',
|
|
reader_cfg=triviaqa_reader_cfg,
|
|
infer_cfg=triviaqa_infer_cfg,
|
|
eval_cfg=triviaqa_eval_cfg)
|
|
)
|