OpenCompass/opencompass/datasets/subjective/__init__.py
bittersweet1999 fa54aa62f6
[Feature] Add Judgerbench and reorg subeval (#1593)
* fix pip version

* fix pip version

* update (#1522)

Co-authored-by: zhulin1 <zhulin1@pjlab.org.cn>

* [Feature] Update Models (#1518)

* Update Models

* Update

* Update humanevalx

* Update

* Update

* [Feature] Dataset prompts update for ARC, BoolQ, Race (#1527)

add judgerbench and reorg sub

add judgerbench and reorg subeval

add judgerbench and reorg subeval

* add judgerbench and reorg subeval

* add judgerbench and reorg subeval

* add judgerbench and reorg subeval

* add judgerbench and reorg subeval

---------

Co-authored-by: zhulinJulia24 <145004780+zhulinJulia24@users.noreply.github.com>
Co-authored-by: zhulin1 <zhulin1@pjlab.org.cn>
Co-authored-by: Songyang Zhang <tonysy@users.noreply.github.com>
Co-authored-by: Linchen Xiao <xxllcc1993@gmail.com>
2024-10-15 16:36:05 +08:00

28 lines
1.6 KiB
Python

# flake8: noqa: F401, F403
from .alignbench import AlignmentBenchDataset # noqa: F401, F403
from .alignbench import alignbench_postprocess # noqa: F401, F403
from .alpacaeval import AlpacaEvalDataset # noqa: F401, F403
from .alpacaeval import alpacaeval_postprocess # noqa: F401, F403
from .arena_hard import ArenaHardDataset # noqa: F401, F403
from .arena_hard import arenahard_postprocess # noqa: F401, F403
from .compassbench import CompassBenchDataset # noqa: F401, F403
from .compassbench_checklist import \
CompassBenchCheklistDataset # noqa: F401, F403
from .compassbench_control_length_bias import \
CompassBenchControlLengthBiasDataset # noqa: F401, F403
from .corev2 import Corev2Dataset # noqa: F401, F403
from .creationbench import CreationBenchDataset # noqa: F401, F403
from .flames import FlamesDataset # noqa: F401, F403
from .fofo import FofoDataset, fofo_postprocess # noqa: F401, F403
from .followbench import FollowBenchDataset # noqa: F401, F403
from .followbench import followbench_postprocess
from .judgerbench import JudgerBenchDataset # noqa: F401, F403
from .judgerbench import JudgerBenchEvaluator # noqa: F401, F403
from .mtbench import MTBenchDataset, mtbench_postprocess # noqa: F401, F403
from .mtbench101 import MTBench101Dataset # noqa: F401, F403
from .mtbench101 import mtbench101_postprocess
from .multiround import MultiroundDataset # noqa: F401, F403
from .subjective_cmp import SubjectiveCmpDataset # noqa: F401, F403
from .wildbench import WildBenchDataset # noqa: F401, F403
from .wildbench import wildbench_postprocess # noqa: F401, F403