mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
46cc7894e1
* [Feature] Support import configs/models/summarizers from whl * Update LCBench configs * Update * Update * Update * Update * update * Update * Update * Update * Update * Update
31 lines
1.0 KiB
Python
31 lines
1.0 KiB
Python
from mmengine.config import read_base
|
|
|
|
with read_base():
|
|
from .groups.mmlu import mmlu_summary_groups
|
|
from .groups.ceval import ceval_summary_groups
|
|
from .groups.bbh import bbh_summary_groups
|
|
from .groups.GaokaoBench import GaokaoBench_summary_groups
|
|
from .groups.cmmlu import cmmlu_summary_groups
|
|
|
|
summarizer = dict(
|
|
dataset_abbrs=[
|
|
['mmlu', 'naive_average'],
|
|
['cmmlu', 'naive_average'],
|
|
['ceval-test', 'naive_average'],
|
|
['GaokaoBench', 'weighted_average'],
|
|
['triviaqa_wiki_1shot', 'score'],
|
|
['nq_open_1shot', 'score'],
|
|
['race-high', 'accuracy'],
|
|
['winogrande', 'accuracy'],
|
|
['hellaswag', 'accuracy'],
|
|
['bbh', 'naive_average'],
|
|
['gsm8k', 'accuracy'],
|
|
['math', 'accuracy'],
|
|
['TheoremQA', 'accuracy'],
|
|
['openai_humaneval', 'humaneval_pass@1'],
|
|
['sanitized_mbpp', 'score'],
|
|
],
|
|
summary_groups=sum(
|
|
[v for k, v in locals().items() if k.endswith('_summary_groups')], []),
|
|
)
|