mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
a0cfd61129
* Update MathBench & WikiBench for FullBench * Update MathBench & WikiBench for FullBench * Update GPQA & MMLU_Pro * Update MathBench & WikiBench for FullBench * Update MathBench & WikiBench for FullBench * Update MathBench & WikiBench for FullBench * Update MathBench & Math base config --------- Co-authored-by: liushz <liuhongwei@pjlab.rog.cn>
31 lines
1.1 KiB
Python
31 lines
1.1 KiB
Python
from mmengine.config import read_base
|
|
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 import MATHDataset, MATHEvaluator, math_postprocess_v2
|
|
|
|
with read_base():
|
|
from .math_4shot_example_from_google_research import prompt
|
|
|
|
math_reader_cfg = dict(input_columns=['problem'], output_column='solution')
|
|
|
|
math_infer_cfg = dict(
|
|
prompt_template=dict(type=PromptTemplate, template=prompt + '\n\nProblem:\n{problem}\nSolution:'),
|
|
retriever=dict(type=ZeroRetriever),
|
|
inferencer=dict(type=GenInferencer, max_out_len=2048, stopping_criteria=['Problem', '问题:']))
|
|
|
|
# postprocess v2
|
|
math_eval_cfg = dict(
|
|
evaluator=dict(type=MATHEvaluator, version='v2'),
|
|
pred_postprocessor=dict(type=math_postprocess_v2))
|
|
|
|
math_datasets = [
|
|
dict(
|
|
type=MATHDataset,
|
|
abbr='math',
|
|
path='opencompass/math',
|
|
reader_cfg=math_reader_cfg,
|
|
infer_cfg=math_infer_cfg,
|
|
eval_cfg=math_eval_cfg)
|
|
]
|