mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
53 lines
1.5 KiB
Python
53 lines
1.5 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 import GPQADataset, GPQA_Simple_Eval_postprocess, GPQAEvaluator
|
|
|
|
# openai_simple_eval prompt
|
|
align_prompt = """
|
|
Answer the following multiple choice question. The last line of your response should be of the following format: 'ANSWER: $LETTER' (without quotes) where LETTER is one of ABCD.
|
|
|
|
{question}
|
|
|
|
A) {A}
|
|
B) {B}
|
|
C) {C}
|
|
D) {D}
|
|
""".strip()
|
|
|
|
gpqa_reader_cfg = dict(
|
|
input_columns=['question', 'A', 'B', 'C', 'D'],
|
|
output_column='answer')
|
|
|
|
gpqa_infer_cfg = dict(
|
|
prompt_template=dict(
|
|
type=PromptTemplate,
|
|
template=dict(
|
|
round=[
|
|
dict(role='HUMAN', prompt=align_prompt),
|
|
], )),
|
|
retriever=dict(type=ZeroRetriever),
|
|
inferencer=dict(type=GenInferencer))
|
|
|
|
gpqa_eval_cfg = dict(evaluator=dict(type=GPQAEvaluator),
|
|
pred_postprocessor=dict(type=GPQA_Simple_Eval_postprocess))
|
|
|
|
gpqa_datasets = []
|
|
gpqa_subsets = {
|
|
# 'extended': 'gpqa_extended.csv',
|
|
# 'main': 'gpqa_main.csv',
|
|
'diamond': 'gpqa_diamond.csv'
|
|
}
|
|
|
|
for split in list(gpqa_subsets.keys()):
|
|
gpqa_datasets.append(
|
|
dict(
|
|
abbr='GPQA_' + split,
|
|
type=GPQADataset,
|
|
path='./data/gpqa/',
|
|
name=gpqa_subsets[split],
|
|
reader_cfg=gpqa_reader_cfg,
|
|
infer_cfg=gpqa_infer_cfg,
|
|
eval_cfg=gpqa_eval_cfg)
|
|
)
|