mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00

* fix lint issues * updated gitignore * changed infer_order from random to double for the pairwise_judge.py (not changing for pairwise_bt_judge.py * added return statement to CompassArenaBradleyTerrySummarizer to return overall score for each judger model
22 lines
969 B
Python
22 lines
969 B
Python
# flake8: noqa: F401, E501
|
|
from .alignmentbench import AlignmentBenchSummarizer
|
|
from .all_obj import AllObjSummarizer
|
|
from .alpacaeval import AlpacaSummarizer
|
|
from .arenahard import ArenaHardSummarizer
|
|
from .charm import CharmMemSummarizer
|
|
from .common_summarizer import CommonSummarizer
|
|
from .compass_arena import CompassArenaSummarizer
|
|
from .compass_arena_bradley_terry import CompassArenaBradleyTerrySummarizer
|
|
from .compassbench import CompassBenchSummarizer
|
|
from .corev2 import Corev2Summarizer
|
|
from .creationbench import CreationBenchSummarizer
|
|
from .flames import FlamesSummarizer
|
|
from .fofo import FofoSummarizer
|
|
from .followbench import FollowBenchSummarizer
|
|
from .mtbench import MTBenchSummarizer
|
|
from .mtbench101 import MTBench101Summarizer
|
|
from .multiround import MultiroundSummarizer
|
|
from .qacompassbench import QaCompassBenchSummarizer
|
|
from .subjective import SubjectiveSummarizer
|
|
from .wildbench import WildBenchPairSummarizer, WildBenchSingleSummarizer
|