mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
73c80953c6
* support dataset repeat and g-pass compute for each evaluator * fix pre-commit errors * delete print * delete gpassk_evaluator and fix potential errors * change `repeat` to `n` * fix `repeat` to `n` in openicl_eval * update doc for multi-run and g-pass * update latex equation in doc * update eng doc for multi-run and g-pass * update datasets.md * update datasets.md * fix multi-line equation * fix multi-line equation * fix multi-line equation * fix multi-line equation * fix multi-line equation * fix multi-line equation * fix multi-line equation in zh_cn user_guides * mmodify pre-commit-zh-cn * recover pre-commit and edit math expr in doc * del [TIP] * del cite tag in doc * del extract_model param in livemathbench config
46 lines
1.2 KiB
Python
46 lines
1.2 KiB
Python
from opencompass.openicl.icl_prompt_template import PromptTemplate
|
|
from opencompass.openicl.icl_retriever import ZeroRetriever
|
|
from opencompass.openicl.icl_inferencer import GenInferencer
|
|
|
|
from opencompass.datasets.livemathbench import LiveMathBenchDataset, LiveMathBenchEvaluator
|
|
|
|
|
|
livemathbench_dataset = dict(
|
|
type=LiveMathBenchDataset,
|
|
path='',
|
|
k=16,
|
|
n=48,
|
|
dataset_splits=['CNMO', 'CCEE', 'AMC', 'WLPMC'],
|
|
dataset_languages=['cn', 'en'],
|
|
cot=True,
|
|
version='202412',
|
|
abbr='LiveMathBench-v202412',
|
|
reader_cfg=dict(
|
|
input_columns=['prompt'],
|
|
output_column='answer'
|
|
),
|
|
infer_cfg=dict(
|
|
prompt_template=dict(
|
|
type=PromptTemplate,
|
|
template=dict(
|
|
round=[
|
|
dict(role='HUMAN', prompt='{prompt}'),
|
|
]
|
|
)
|
|
),
|
|
retriever=dict(type=ZeroRetriever),
|
|
inferencer=dict(
|
|
type=GenInferencer,
|
|
max_out_len=8192
|
|
),
|
|
),
|
|
eval_cfg=dict(
|
|
evaluator=dict(
|
|
type=LiveMathBenchEvaluator,
|
|
model_name='',
|
|
url=[]
|
|
)
|
|
)
|
|
)
|
|
livemathbench_datasets = [livemathbench_dataset]
|