This commit is contained in:
huihui 2025-05-09 04:46:47 +00:00
parent 70192c284b
commit efae720249
3 changed files with 4 additions and 3 deletions

View File

@ -89,4 +89,5 @@ sciknoweval_dataset_physics = dict(
eval_cfg=eval_cfg,
)
sciknoweval_datasets = [sciknoweval_dataset_biology, sciknoweval_dataset_chemistry, sciknoweval_dataset_physics, sciknoweval_dataset_material]

View File

@ -1,4 +1,4 @@
from opencompass.datasets import SciKnowEvalDataset, SciKnowEvalEvaluator
from opencompass.datasets import SciKnowEvalDataset
from opencompass.datasets import generic_llmjudge_postprocess
from opencompass.openicl.icl_inferencer import GenInferencer
from opencompass.openicl.icl_prompt_template import PromptTemplate
@ -6,7 +6,6 @@ from opencompass.openicl.icl_retriever import ZeroRetriever
from opencompass.evaluator import GenericLLMEvaluator
ZERO_SHOT_PROMPT = '{q4}'
GRADER_TEMPLATE = """
Please as a grading expert, judge whether the final answers given by the candidates below are consistent with the standard answers, that is, whether the candidates answered correctly.

View File

@ -130,7 +130,8 @@ from .ruler import * # noqa: F401, F403
from .safety import * # noqa: F401, F403
from .scibench import ScibenchDataset, scibench_postprocess # noqa: F401, F403
from .scicode import * # noqa: F401, F403
from .SciKnowEval import * # noqa: F401, F403
from .SciKnowEval import SciKnowEvalDataset # noqa: F401, F403
from .SciKnowEval import SciKnowEvalEvaluator # noqa: F401, F403
from .simpleqa import * # noqa: F401, F403
from .siqa import * # noqa: F401, F403
from .smolinstruct import * # noqa: F401, F403