Update configs (#9)

* Update implements

* Update

configs/datasets/agieval/agieval_gen_397d81.py

@@ -3,6 +3,7 @@ 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 AGIEvalDataset_v2, AGIEvalEvaluator
+from opencompass.utils.text_postprocessors import first_capital_postprocess, first_capital_postprocess_multi
 
 agieval_reader_cfg = dict(
     input_columns=['question', 'options'], output_column='label')
@@ -82,7 +83,7 @@ for _name in agieval_single_choice_sets:
 
     agieval_eval_cfg = dict(
         evaluator=dict(type=AccEvaluator),
-        pred_postprocessor=dict(type='first-capital'))
+        pred_postprocessor=dict(type=first_capital_postprocess))
 
     agieval_datasets.append(
         dict(
@@ -111,7 +112,7 @@ for _name in agieval_multiple_choices_sets:
 
     agieval_eval_cfg = dict(
         evaluator=dict(type=AccEvaluator),
-        pred_postprocessor=dict(type='first-capital-multi'))
+        pred_postprocessor=dict(type=first_capital_postprocess_multi))
 
     agieval_datasets.append(
         dict(

configs/datasets/agieval/agieval_mixed_2f14ad.py

@@ -3,6 +3,7 @@ from opencompass.openicl.icl_retriever import ZeroRetriever
 from opencompass.openicl.icl_inferencer import PPLInferencer, GenInferencer
 from opencompass.openicl.icl_evaluator import AccEvaluator
 from opencompass.datasets import AGIEvalDataset_v2, AGIEvalEvaluator
+from opencompass.utils.text_postprocessors import first_capital_postprocess_multi
 
 agieval_single_choice_sets = [
     'gaokao-chinese',
@@ -116,7 +117,7 @@ for _name in agieval_multiple_choices_sets:
 
     agieval_eval_cfg = dict(
         evaluator=dict(type=AccEvaluator),
-        pred_postprocessor=dict(type='first-capital-multi'))
+        pred_postprocessor=dict(type=first_capital_postprocess_multi))
 
     agieval_datasets.append(
         dict(

configs/datasets/apps/apps_gen_5b4254.py

 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 HFDataset, HumanEvaluator
+from opencompass.datasets import HFDataset, HumanEvaluator, humaneval_postprocess
 
 apps_reader_cfg = dict(
     input_columns=['question'], output_column='problem_id', train_split='test')
@@ -20,7 +20,7 @@ apps_eval_cfg = dict(
     evaluator=dict(type=HumanEvaluator),
     pred_role='BOT',
     k=[1, 10, 100],  # the parameter only for humaneval
-    pred_postprocessor=dict(type='humaneval'),
+    pred_postprocessor=dict(type=humaneval_postprocess),
 )
 
 apps_datasets = [

configs/datasets/apps/apps_gen_7fbb95.py

 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 HFDataset, HumanEvaluator
+from opencompass.datasets import HFDataset, HumanEvaluator, humaneval_postprocess
 
 apps_reader_cfg = dict(
     input_columns=['question'], output_column='problem_id', train_split='test')
@@ -27,7 +27,7 @@ apps_eval_cfg = dict(
     evaluator=dict(type=HumanEvaluator),
     pred_role='BOT',
     k=[1, 10, 100],  # the parameter only for humaneval
-    pred_postprocessor=dict(type='humaneval'),
+    pred_postprocessor=dict(type=humaneval_postprocess),
 )
 
 apps_datasets = [

configs/datasets/apps/apps_gen_b4dee3.py

 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 HFDataset, HumanEvaluator
+from opencompass.datasets import HFDataset, HumanEvaluator, humaneval_postprocess
 
 apps_reader_cfg = dict(
     input_columns=['question'], output_column='problem_id', train_split='test')
@@ -17,7 +17,7 @@ apps_infer_cfg = dict(
 apps_eval_cfg = dict(
     evaluator=dict(type=HumanEvaluator),
     k=[1, 10, 100],
-    pred_postprocessor=dict(type='humaneval'),
+    pred_postprocessor=dict(type=humaneval_postprocess),
 )
 
 apps_datasets = [

configs/datasets/bbh/bbh_gen.py

 from mmengine.config import read_base
 
 with read_base():
-    from .bbh_gen_6bd693 import bbh_datasets  # noqa: F401, F403
+    from .bbh_gen_5b92b0 import bbh_datasets  # noqa: F401, F403

configs/datasets/bbh/bbh_gen_6bd693.py → configs/datasets/bbh/bbh_gen_5b92b0.py

@@ -3,7 +3,7 @@ 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 BBHDataset, BBHEvaluator
+from opencompass.datasets import BBHDataset, BBHEvaluator, bbh_mcq_postprocess
 
 bbh_reader_cfg = dict(input_columns=["input"], output_column="target")
 
@@ -61,8 +61,8 @@ for _name in bbh_multiple_choice_sets:
     bbh_eval_cfg = dict(
         evaluator=dict(type=AccEvaluator),
         pred_role="BOT",
-        pred_postprocessor=dict(type='bbh-mcq'),
-        dataset_postprocessor=dict(type='bbh-mcq'))
+        pred_postprocessor=dict(type=bbh_mcq_postprocess),
+        dataset_postprocessor=dict(type=bbh_mcq_postprocess))
 
     bbh_datasets.append(
         dict(

configs/datasets/ceval/ceval_gen_2daf24.py

@@ -3,6 +3,7 @@ from opencompass.openicl.icl_retriever import FixKRetriever
 from opencompass.openicl.icl_inferencer import GenInferencer
 from opencompass.openicl.icl_evaluator import AccEvaluator
 from opencompass.datasets import CEvalDataset
+from opencompass.utils.text_postprocessors import first_capital_postprocess
 
 ceval_subject_mapping = {
     "computer_network":
@@ -166,7 +167,7 @@ for _split in ["val", "test"]:
 
         ceval_eval_cfg = dict(
             evaluator=dict(type=AccEvaluator),
-            pred_postprocessor=dict(type='first-capital'))
+            pred_postprocessor=dict(type=first_capital_postprocess))
 
         ceval_datasets.append(
             dict(

configs/datasets/ceval/ceval_gen_5f30c7.py

@@ -3,6 +3,7 @@ from opencompass.openicl.icl_retriever import FixKRetriever
 from opencompass.openicl.icl_inferencer import GenInferencer
 from opencompass.openicl.icl_evaluator import AccEvaluator
 from opencompass.datasets import CEvalDataset
+from opencompass.utils.text_postprocessors import first_capital_postprocess
 
 ceval_subject_mapping = {
     "computer_network":
@@ -164,7 +165,9 @@ for _split in ["val"]:
             inferencer=dict(type=GenInferencer, fix_id_list=[0, 1, 2, 3, 4]),
         )
 
-        ceval_eval_cfg = dict(evaluator=dict(type=AccEvaluator), )
+        ceval_eval_cfg = dict(
+            evaluator=dict(type=AccEvaluator),
+            pred_postprocessor=dict(type=first_capital_postprocess))
 
         ceval_datasets.append(
             dict(

configs/datasets/collections/base_medium.py

@@ -5,18 +5,18 @@ with read_base():
     from ..ceval.ceval_ppl_578f8d import ceval_datasets
     from ..agieval.agieval_mixed_2f14ad import agieval_datasets
     from ..GaokaoBench.GaokaoBench_mixed_f2038e import GaokaoBench_datasets
-    from ..bbh.bbh_gen_6bd693 import bbh_datasets
+    from ..bbh.bbh_gen_5b92b0 import bbh_datasets
     from ..humaneval.humaneval_gen_8e312c import humaneval_datasets
     from ..mbpp.mbpp_gen_1e1056 import mbpp_datasets
     from ..CLUE_C3.CLUE_C3_ppl_e24a31 import C3_datasets
-    from ..CLUE_CMRC.CLUE_CMRC_gen_941108 import CMRC_datasets
-    from ..CLUE_DRCD.CLUE_DRCD_gen_941108 import DRCD_datasets
+    from ..CLUE_CMRC.CLUE_CMRC_gen_1bd3c8 import CMRC_datasets
+    from ..CLUE_DRCD.CLUE_DRCD_gen_1bd3c8 import DRCD_datasets
     from ..CLUE_afqmc.CLUE_afqmc_ppl_6507d7 import afqmc_datasets
     from ..CLUE_cmnli.CLUE_cmnli_ppl_fdc6de import cmnli_datasets
     from ..CLUE_ocnli.CLUE_ocnli_ppl_fdc6de import ocnli_datasets
     from ..FewCLUE_bustm.FewCLUE_bustm_ppl_e53034 import bustm_datasets
     from ..FewCLUE_chid.FewCLUE_chid_ppl_8f2872 import chid_datasets
-    from ..FewCLUE_cluewsc.FewCLUE_cluewsc_ppl_868415 import cluewsc_datasets
+    from ..FewCLUE_cluewsc.FewCLUE_cluewsc_ppl_4284a0 import cluewsc_datasets
     from ..FewCLUE_csl.FewCLUE_csl_ppl_841b62 import csl_datasets
     from ..FewCLUE_eprstmt.FewCLUE_eprstmt_ppl_f1e631 import eprstmt_datasets
     from ..FewCLUE_ocnli_fc.FewCLUE_ocnli_fc_ppl_c08300 import ocnli_fc_datasets
@@ -33,24 +33,24 @@ with read_base():
     from ..SuperGLUE_RTE.SuperGLUE_RTE_ppl_66caf3 import RTE_datasets
     from ..SuperGLUE_ReCoRD.SuperGLUE_ReCoRD_gen_30dea0 import ReCoRD_datasets
     from ..SuperGLUE_WiC.SuperGLUE_WiC_ppl_312de9 import WiC_datasets
-    from ..SuperGLUE_WSC.SuperGLUE_WSC_ppl_d0f531 import WSC_datasets
-    from ..race.race_ppl_ab8734 import race_datasets
+    from ..SuperGLUE_WSC.SuperGLUE_WSC_ppl_003529 import WSC_datasets
+    from ..race.race_ppl_a138cd import race_datasets
     from ..Xsum.Xsum_gen_31397e import Xsum_datasets
     from ..gsm8k.gsm8k_gen_1d7fe4 import gsm8k_datasets
     from ..summedits.summedits_ppl_1fbeb6 import summedits_datasets
-    from ..math.math_gen_3e92f6 import math_datasets
-    from ..TheoremQA.TheoremQA_gen_8acdf7 import TheoremQA_datasets
+    from ..math.math_gen_265cce import math_datasets
+    from ..TheoremQA.TheoremQA_gen_ef26ca import TheoremQA_datasets
     from ..hellaswag.hellaswag_ppl_47bff9 import hellaswag_datasets
     from ..ARC_e.ARC_e_ppl_a450bd import ARC_e_datasets
     from ..ARC_c.ARC_c_ppl_a450bd import ARC_c_datasets
     from ..commonsenseqa.commonsenseqa_ppl_5545e2 import commonsenseqa_datasets
     from ..piqa.piqa_ppl_1cf9f0 import piqa_datasets
     from ..siqa.siqa_ppl_ced5f6 import siqa_datasets
-    from ..strategyqa.strategyqa_gen_b3ff20 import strategyqa_datasets
-    from ..winogrande.winogrande_ppl_18e5de import winogrande_datasets
+    from ..strategyqa.strategyqa_gen_1180a7 import strategyqa_datasets
+    from ..winogrande.winogrande_ppl_55a66e import winogrande_datasets
     from ..obqa.obqa_ppl_c7c154 import obqa_datasets
-    from ..nq.nq_gen_3dcea1 import nq_datasets
-    from ..triviaqa.triviaqa_gen_3e39a5 import triviaqa_datasets
+    from ..nq.nq_gen_c788f6 import nq_datasets
+    from ..triviaqa.triviaqa_gen_2121ce import triviaqa_datasets
     from ..flores.flores_gen_806ede import flores_datasets
     from ..crowspairs.crowspairs_ppl_e811e1 import crowspairs_datasets
 

configs/datasets/collections/base_small.py

@@ -2,9 +2,9 @@ from mmengine.config import read_base
 
 with read_base():
     from ..ceval.ceval_ppl_578f8d import ceval_datasets
-    from ..bbh.bbh_gen_6bd693 import bbh_datasets
-    from ..CLUE_CMRC.CLUE_CMRC_gen_941108 import CMRC_datasets
-    from ..CLUE_DRCD.CLUE_DRCD_gen_941108 import DRCD_datasets
+    from ..bbh.bbh_gen_5b92b0 import bbh_datasets
+    from ..CLUE_CMRC.CLUE_CMRC_gen_1bd3c8 import CMRC_datasets
+    from ..CLUE_DRCD.CLUE_DRCD_gen_1bd3c8 import DRCD_datasets
     from ..CLUE_afqmc.CLUE_afqmc_ppl_6507d7 import afqmc_datasets
     from ..FewCLUE_bustm.FewCLUE_bustm_ppl_e53034 import bustm_datasets
     from ..FewCLUE_chid.FewCLUE_chid_ppl_8f2872 import chid_datasets
@@ -24,16 +24,16 @@ with read_base():
     from ..SuperGLUE_ReCoRD.SuperGLUE_ReCoRD_gen_30dea0 import ReCoRD_datasets
     from ..SuperGLUE_WiC.SuperGLUE_WiC_ppl_312de9 import WiC_datasets
     from ..SuperGLUE_WSC.SuperGLUE_WSC_ppl_d0f531 import WSC_datasets
-    from ..race.race_ppl_ab8734 import race_datasets
-    from ..math.math_gen_3e92f6 import math_datasets
+    from ..race.race_ppl_a138cd import race_datasets
+    from ..math.math_gen_265cce import math_datasets
     from ..gsm8k.gsm8k_gen_1d7fe4 import gsm8k_datasets
     from ..summedits.summedits_ppl_1fbeb6 import summedits_datasets
     from ..hellaswag.hellaswag_ppl_47bff9 import hellaswag_datasets
     from ..piqa.piqa_ppl_1cf9f0 import piqa_datasets
-    from ..winogrande.winogrande_ppl_18e5de import winogrande_datasets
+    from ..winogrande.winogrande_ppl_55a66e import winogrande_datasets
     from ..obqa.obqa_ppl_c7c154 import obqa_datasets
-    from ..nq.nq_gen_3dcea1 import nq_datasets
-    from ..triviaqa.triviaqa_gen_3e39a5 import triviaqa_datasets
+    from ..nq.nq_gen_c788f6 import nq_datasets
+    from ..triviaqa.triviaqa_gen_2121ce import triviaqa_datasets
     from ..crowspairs.crowspairs_ppl_e811e1 import crowspairs_datasets
 
 datasets = sum((v for k, v in locals().items() if k.endswith('_datasets')), [])

configs/datasets/collections/chat_medium.py

@@ -5,19 +5,19 @@ with read_base():
     from ..ceval.ceval_gen_5f30c7 import ceval_datasets
     from ..agieval.agieval_gen_397d81 import agieval_datasets
     from ..GaokaoBench.GaokaoBench_gen_5cfe9e import GaokaoBench_datasets
-    from ..bbh.bbh_gen_6bd693 import bbh_datasets
+    from ..bbh.bbh_gen_5b92b0 import bbh_datasets
     from ..humaneval.humaneval_gen_8e312c import humaneval_datasets
     from ..mbpp.mbpp_gen_1e1056 import mbpp_datasets
     from ..CLUE_C3.CLUE_C3_gen_8c358f import C3_datasets
-    from ..CLUE_CMRC.CLUE_CMRC_gen_941108 import CMRC_datasets
-    from ..CLUE_DRCD.CLUE_DRCD_gen_941108 import DRCD_datasets
+    from ..CLUE_CMRC.CLUE_CMRC_gen_1bd3c8 import CMRC_datasets
+    from ..CLUE_DRCD.CLUE_DRCD_gen_1bd3c8 import DRCD_datasets
     from ..CLUE_afqmc.CLUE_afqmc_gen_901306 import afqmc_datasets
     from ..CLUE_cmnli.CLUE_cmnli_gen_1abf97 import cmnli_datasets
     from ..CLUE_ocnli.CLUE_ocnli_gen_c4cb6c import ocnli_datasets
     from ..FewCLUE_bustm.FewCLUE_bustm_gen_634f41 import bustm_datasets
     from ..FewCLUE_chid.FewCLUE_chid_gen_0a29a2 import chid_datasets
     from ..FewCLUE_cluewsc.FewCLUE_cluewsc_gen_c68933 import cluewsc_datasets
-    from ..FewCLUE_csl.FewCLUE_csl_gen_87f4a8 import csl_datasets
+    from ..FewCLUE_csl.FewCLUE_csl_gen_28b223 import csl_datasets
     from ..FewCLUE_eprstmt.FewCLUE_eprstmt_gen_740ea0 import eprstmt_datasets
     from ..FewCLUE_ocnli_fc.FewCLUE_ocnli_fc_gen_f97a97 import ocnli_fc_datasets
     from ..FewCLUE_tnews.FewCLUE_tnews_gen_b90e4a import tnews_datasets
@@ -37,20 +37,20 @@ with read_base():
     from ..race.race_gen_69ee4f import race_datasets
     from ..Xsum.Xsum_gen_31397e import Xsum_datasets
     from ..gsm8k.gsm8k_gen_1d7fe4 import gsm8k_datasets
-    from ..summedits.summedits_gen_4fb38b import summedits_datasets
-    from ..math.math_gen_3e92f6 import math_datasets
-    from ..TheoremQA.TheoremQA_gen_a27a10 import TheoremQA_datasets
+    from ..summedits.summedits_gen_315438 import summedits_datasets
+    from ..math.math_gen_265cce import math_datasets
+    from ..TheoremQA.TheoremQA_gen_7009de import TheoremQA_datasets
     from ..hellaswag.hellaswag_gen_6faab5 import hellaswag_datasets
     from ..ARC_e.ARC_e_gen_1e0de5 import ARC_e_datasets
     from ..ARC_c.ARC_c_gen_1e0de5 import ARC_c_datasets
     from ..commonsenseqa.commonsenseqa_gen_c946f2 import commonsenseqa_datasets
     from ..piqa.piqa_gen_1194eb import piqa_datasets
     from ..siqa.siqa_gen_e78df3 import siqa_datasets
-    from ..strategyqa.strategyqa_gen_b3ff20 import strategyqa_datasets
+    from ..strategyqa.strategyqa_gen_1180a7 import strategyqa_datasets
     from ..winogrande.winogrande_gen_a9ede5 import winogrande_datasets
     from ..obqa.obqa_gen_9069e4 import obqa_datasets
-    from ..nq.nq_gen_68c1c6 import nq_datasets
-    from ..triviaqa.triviaqa_gen_3e39a5 import triviaqa_datasets
+    from ..nq.nq_gen_c788f6 import nq_datasets
+    from ..triviaqa.triviaqa_gen_2121ce import triviaqa_datasets
     from ..flores.flores_gen_806ede import flores_datasets
     from ..crowspairs.crowspairs_gen_02b6c1 import crowspairs_datasets
 

configs/datasets/collections/chat_small.py

@@ -3,9 +3,9 @@ from mmengine.config import read_base
 with read_base():
     from ..mmlu.mmlu_gen_a484b3 import mmlu_datasets
     from ..ceval.ceval_gen_5f30c7 import ceval_datasets
-    from ..bbh.bbh_gen_6bd693 import bbh_datasets
-    from ..CLUE_CMRC.CLUE_CMRC_gen_941108 import CMRC_datasets
-    from ..CLUE_DRCD.CLUE_DRCD_gen_941108 import DRCD_datasets
+    from ..bbh.bbh_gen_5b92b0 import bbh_datasets
+    from ..CLUE_CMRC.CLUE_CMRC_gen_1bd3c8 import CMRC_datasets
+    from ..CLUE_DRCD.CLUE_DRCD_gen_1bd3c8 import DRCD_datasets
     from ..CLUE_afqmc.CLUE_afqmc_gen_901306 import afqmc_datasets
     from ..FewCLUE_bustm.FewCLUE_bustm_gen_634f41 import bustm_datasets
     from ..FewCLUE_chid.FewCLUE_chid_gen_0a29a2 import chid_datasets
@@ -24,17 +24,17 @@ with read_base():
     from ..SuperGLUE_RTE.SuperGLUE_RTE_gen_68aac7 import RTE_datasets
     from ..SuperGLUE_ReCoRD.SuperGLUE_ReCoRD_gen_30dea0 import ReCoRD_datasets
     from ..SuperGLUE_WiC.SuperGLUE_WiC_gen_d06864 import WiC_datasets
-    from ..SuperGLUE_WSC.SuperGLUE_WSC_gen_6dc406 import WSC_datasets
+    from ..SuperGLUE_WSC.SuperGLUE_WSC_gen_8a881c import WSC_datasets
     from ..race.race_gen_69ee4f import race_datasets
-    from ..math.math_gen_3e92f6 import math_datasets
+    from ..math.math_gen_265cce import math_datasets
     from ..gsm8k.gsm8k_gen_1d7fe4 import gsm8k_datasets
-    from ..summedits.summedits_gen_4fb38b import summedits_datasets
+    from ..summedits.summedits_gen_315438 import summedits_datasets
     from ..hellaswag.hellaswag_gen_6faab5 import hellaswag_datasets
     from ..piqa.piqa_gen_1194eb import piqa_datasets
     from ..winogrande.winogrande_gen_a9ede5 import winogrande_datasets
     from ..obqa.obqa_gen_9069e4 import obqa_datasets
-    from ..nq.nq_gen_68c1c6 import nq_datasets
-    from ..triviaqa.triviaqa_gen_3e39a5 import triviaqa_datasets
+    from ..nq.nq_gen_c788f6 import nq_datasets
+    from ..triviaqa.triviaqa_gen_2121ce import triviaqa_datasets
     from ..crowspairs.crowspairs_gen_02b6c1 import crowspairs_datasets
 
 datasets = sum((v for k, v in locals().items() if k.endswith('_datasets')), [])

configs/datasets/collections/example.py

@@ -2,6 +2,6 @@ from mmengine.config import read_base
 
 with read_base():
     from ..piqa.piqa_gen_1194eb import piqa_datasets
-    from ..nq.nq_gen_68c1c6 import nq_datasets
+    from ..nq.nq_gen_c788f6 import nq_datasets
 
 datasets = sum((v for k, v in locals().items() if k.endswith('_datasets')), [])

configs/datasets/commonsenseqa/commonsenseqa_gen_c946f2.py

@@ -3,6 +3,7 @@ from opencompass.openicl.icl_retriever import MDLRetriever
 from opencompass.openicl.icl_inferencer import GenInferencer
 from opencompass.openicl.icl_evaluator import AccEvaluator
 from opencompass.datasets import commonsenseqaDataset
+from opencompass.utils.text_postprocessors import first_capital_postprocess
 
 commonsenseqa_reader_cfg = dict(
     input_columns=["question", "A", "B", "C", "D", "E"],
@@ -44,7 +45,7 @@ commonsenseqa_infer_cfg = dict(
 
 commonsenseqa_eval_cfg = dict(
     evaluator=dict(type=AccEvaluator),
-    pred_postprocessor=dict(type="first-capital"),
+    pred_postprocessor=dict(type=first_capital_postprocess),
 )
 
 commonsenseqa_datasets = [

configs/datasets/crowspairs/crowspairs_gen_02b6c1.py

@@ -3,10 +3,11 @@ 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 crowspairsDataset_V2
+from opencompass.utils.text_postprocessors import first_capital_postprocess
 
 crowspairs_reader_cfg = dict(
     input_columns=['sent_more', 'sent_less'],
-    output_column='id',
+    output_column='label',
     train_split='test',
     test_split='test')
 
@@ -26,7 +27,7 @@ crowspairs_infer_cfg = dict(
 crowspairs_eval_cfg = dict(
     evaluator=dict(type=AccEvaluator),
     pred_role="BOT",
-    pred_postprocessor=dict(type="first-capital"),
+    pred_postprocessor=dict(type=first_capital_postprocess),
 )
 
 crowspairs_datasets = [

configs/datasets/crowspairs/crowspairs_ppl_47f211.py

@@ -6,7 +6,7 @@ from opencompass.datasets import crowspairsDataset
 
 crowspairs_reader_cfg = dict(
     input_columns=['sent_more', 'sent_less'],
-    output_column='id',
+    output_column='label',
     train_split='test',
     test_split='test')
 

configs/datasets/crowspairs/crowspairs_ppl_e811e1.py

@@ -6,7 +6,7 @@ from opencompass.datasets import crowspairsDataset
 
 crowspairs_reader_cfg = dict(
     input_columns=['sent_more', 'sent_less'],
-    output_column='id',
+    output_column='label',
     train_split='test',
     test_split='test')
 

configs/datasets/govrepcrs/govrepcrs_gen_aa5eb3.py

@@ -3,6 +3,7 @@ from opencompass.openicl.icl_retriever import ZeroRetriever
 from opencompass.openicl.icl_inferencer import GenInferencer
 from opencompass.openicl.icl_evaluator import BleuEvaluator
 from opencompass.datasets import GovRepcrsDataset
+from opencompass.utils.text_postprocessors import general_cn_postprocess
 
 govrepcrs_reader_cfg = dict(
     input_columns='content',
@@ -21,8 +22,8 @@ govrepcrs_infer_cfg = dict(
 
 govrepcrs_eval_cfg = dict(
     evaluator=dict(type=BleuEvaluator),
-    pred_postprocessor=dict(type='general_cn'),
-    dataset_postprocessor=dict(type='general_cn'))
+    pred_postprocessor=dict(type=general_cn_postprocess),
+    dataset_postprocessor=dict(type=general_cn_postprocess))
 
 govrepcrs_datasets = [
     dict(

configs/datasets/govrepcrs/govrepcrs_gen_db7930.py

@@ -3,6 +3,7 @@ from opencompass.openicl.icl_retriever import ZeroRetriever
 from opencompass.openicl.icl_inferencer import GenInferencer
 from opencompass.openicl.icl_evaluator import BleuEvaluator
 from opencompass.datasets import GovRepcrsDataset
+from opencompass.utils.text_postprocessors import general_cn_postprocess
 
 govrepcrs_reader_cfg = dict(
     input_columns='content',
@@ -33,8 +34,8 @@ govrepcrs_infer_cfg = dict(
 govrepcrs_eval_cfg = dict(
     evaluator=dict(type=BleuEvaluator),
     pred_role='BOT',
-    pred_postprocessor=dict(type='general_cn'),
-    dataset_postprocessor=dict(type='general_cn'))
+    pred_postprocessor=dict(type=general_cn_postprocess),
+    dataset_postprocessor=dict(type=general_cn_postprocess))
 
 govrepcrs_datasets = [
     dict(