mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
65 lines
1.9 KiB
Python
65 lines
1.9 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.openicl.icl_evaluator import AccEvaluator
|
|
from opencompass.datasets import MMLUProDataset
|
|
from opencompass.utils.text_postprocessors import match_answer_pattern
|
|
|
|
with read_base():
|
|
from .mmlu_pro_categories import categories
|
|
|
|
|
|
|
|
QUERY_TEMPLATE = """
|
|
Answer the following multiple choice question. Your response should be of the following format: 'ANSWER: $LETTER' (without quotes) where LETTER is one of Options(e.g. one of ABCDEFGHIJKLMNOP). Please answer directly without additional explanations.
|
|
|
|
Question:\n
|
|
{question}
|
|
|
|
Options:\n
|
|
{options_str}
|
|
|
|
""".strip()
|
|
|
|
mmlu_pro_datasets = []
|
|
|
|
for category in categories:
|
|
mmlu_pro_reader_cfg = dict(
|
|
input_columns=['question', 'cot_content', 'options_str'],
|
|
output_column='answer',
|
|
train_split='validation',
|
|
test_split='test',
|
|
)
|
|
mmlu_pro_infer_cfg = dict(
|
|
prompt_template=dict(
|
|
type=PromptTemplate,
|
|
template=dict(
|
|
round=[
|
|
dict(role='HUMAN',
|
|
prompt=QUERY_TEMPLATE),
|
|
],
|
|
),
|
|
),
|
|
retriever=dict(type=ZeroRetriever),
|
|
inferencer=dict(type=GenInferencer),
|
|
)
|
|
|
|
mmlu_pro_eval_cfg = dict(
|
|
evaluator=dict(type=AccEvaluator),
|
|
pred_postprocessor=dict(
|
|
type=match_answer_pattern,
|
|
answer_pattern=r'(?i)ANSWER\s*:\s*([A-P])')
|
|
)
|
|
|
|
mmlu_pro_datasets.append(
|
|
dict(
|
|
abbr=f'mmlu_pro_{category.replace(" ", "_")}',
|
|
type=MMLUProDataset,
|
|
path='opencompass/mmlu_pro',
|
|
category=category,
|
|
reader_cfg=mmlu_pro_reader_cfg,
|
|
infer_cfg=mmlu_pro_infer_cfg,
|
|
eval_cfg=mmlu_pro_eval_cfg,
|
|
))
|