EuroEval 16.4.0__py3-none-any.whl → 16.5.0__py3-none-any.whl

euroeval/dataset_configs/__init__.py

@@ -3,6 +3,7 @@
 from ..data_models import DatasetConfig
 from ..languages import get_all_languages
 from ..tasks import SPEED
+from .bulgarian import *  # noqa: F403
 from .czech import *  # noqa: F403
 from .danish import *  # noqa: F403
 from .dutch import *  # noqa: F403
@@ -12,6 +13,7 @@ from .faroese import *  # noqa: F403
 from .finnish import *  # noqa: F403
 from .french import *  # noqa: F403
 from .german import *  # noqa: F403
+from .greek import *  # noqa: F403
 from .icelandic import *  # noqa: F403
 from .italian import *  # noqa: F403
 from .latvian import *  # noqa: F403
@@ -19,9 +21,11 @@ from .lithuanian import *  # noqa: F403
 from .norwegian import *  # noqa: F403
 from .polish import *  # noqa: F403
 from .portuguese import *  # noqa: F403
+from .serbian import *  # noqa: F403
 from .slovak import *  # noqa: F403
 from .spanish import *  # noqa: F403
 from .swedish import *  # noqa: F403
+from .ukrainian import *  # noqa: F403
 
 
 def get_all_dataset_configs() -> dict[str, DatasetConfig]:
@@ -31,7 +35,9 @@ def get_all_dataset_configs() -> dict[str, DatasetConfig]:
         A mapping between names of datasets and their configurations.
     """
     dataset_configs = [
-        cfg for cfg in globals().values() if isinstance(cfg, DatasetConfig)
+        cfg
+        for cfg in globals().values()
+        if isinstance(cfg, DatasetConfig) and cfg.task != SPEED
     ]
     assert len(dataset_configs) == len({cfg.name for cfg in dataset_configs}), (
         "There are duplicate dataset configurations. Please ensure that each dataset "
@@ -62,8 +68,9 @@ def get_dataset_config(dataset_name: str) -> DatasetConfig:
 
 SPEED_CONFIG = DatasetConfig(
     name="speed",
-    pretty_name="the speed estimation benchmark",
-    huggingface_id="",
+    pretty_name="",
+    source="",
     task=SPEED,
     languages=list(get_all_languages().values()),
+    _logging_string="the speed estimation benchmark",
 )

euroeval/dataset_configs/bulgarian.py

@@ -0,0 +1,56 @@
+"""All Bulgarian dataset configurations used in EuroEval."""
+
+from ..data_models import DatasetConfig
+from ..languages import BULGARIAN
+from ..tasks import COMMON_SENSE, KNOW, LA, NER, RC, SENT
+
+### Official datasets ###
+
+CINEXIO_CONFIG = DatasetConfig(
+    name="cinexio",
+    pretty_name="Cinexio",
+    source="EuroEval/cinexio-mini",
+    task=SENT,
+    languages=[BULGARIAN],
+)
+
+SCALA_BG_CONFIG = DatasetConfig(
+    name="scala-bg",
+    pretty_name="ScaLA-bg",
+    source="EuroEval/scala-bg",
+    task=LA,
+    languages=[BULGARIAN],
+)
+
+BG_NER_BSNLP_CONFIG = DatasetConfig(
+    name="bg-ner-bsnlp",
+    pretty_name="BG-NER-BSNLp",
+    source="EuroEval/bg-ner-bsnlp-mini",
+    task=NER,
+    languages=[BULGARIAN],
+)
+
+MULTI_WIKI_QA_BG_CONFIG = DatasetConfig(
+    name="multi-wiki-qa-bg",
+    pretty_name="MultiWikiQA-bg",
+    source="EuroEval/multi-wiki-qa-bg-mini",
+    task=RC,
+    languages=[BULGARIAN],
+)
+
+EXAMS_BG_CONFIG = DatasetConfig(
+    name="exams-bg",
+    pretty_name="Exams-bg",
+    source="EuroEval/exams-bg-mini",
+    task=KNOW,
+    languages=[BULGARIAN],
+)
+
+WINOGRANDE_BG_CONFIG = DatasetConfig(
+    name="winogrande-bg",
+    pretty_name="Winogrande-bg",
+    source="EuroEval/winogrande-bg",
+    task=COMMON_SENSE,
+    languages=[BULGARIAN],
+    _labels=["a", "b"],
+)

euroeval/dataset_configs/czech.py

@@ -1,69 +1,65 @@
 """All Czech dataset configurations used in EuroEval."""
 
 from ..data_models import DatasetConfig
-from ..languages import CS
+from ..languages import CZECH
 from ..tasks import COMMON_SENSE, KNOW, LA, NER, RC, SENT, SUMM
 
 ### Official datasets ###
 
 CSFD_SENTIMENT_CONFIG = DatasetConfig(
     name="csfd-sentiment",
-    pretty_name="the truncated version of the Czech sentiment classification dataset "
-    "CSFD Sentiment",
-    huggingface_id="EuroEval/csfd-sentiment-mini",
+    pretty_name="CSFD Sentiment",
+    source="EuroEval/csfd-sentiment-mini",
     task=SENT,
-    languages=[CS],
+    languages=[CZECH],
 )
 
 CS_GEC_CONFIG = DatasetConfig(
     name="cs-gec",
-    pretty_name="the truncated version of the Czech linguistic acceptability dataset "
-    "CS-GEC",
-    huggingface_id="EuroEval/cs-gec-mini",
+    pretty_name="CS-GEC",
+    source="EuroEval/cs-gec-mini",
     task=LA,
-    languages=[CS],
+    languages=[CZECH],
 )
 
 PONER_CONFIG = DatasetConfig(
     name="poner",
-    pretty_name="the truncated version of the Czech named entity recognition dataset "
-    "PONER",
-    huggingface_id="EuroEval/poner-mini",
+    pretty_name="PoNER",
+    source="EuroEval/poner-mini",
     task=NER,
-    languages=[CS],
+    languages=[CZECH],
 )
 
 SQAD_CONFIG = DatasetConfig(
     name="sqad",
-    pretty_name="the truncated version of the Czech reading comprehension dataset SQAD",
-    huggingface_id="EuroEval/sqad-mini",
+    pretty_name="SQAD",
+    source="EuroEval/sqad-mini",
     task=RC,
-    languages=[CS],
+    languages=[CZECH],
 )
 
 CZECH_NEWS_CONFIG = DatasetConfig(
     name="czech-news",
-    pretty_name="the truncated version of the Czech summarisation dataset",
-    huggingface_id="EuroEval/czech-news-mini",
+    pretty_name="Czech News",
+    source="EuroEval/czech-news-mini",
     task=SUMM,
-    languages=[CS],
+    languages=[CZECH],
 )
 
 UMIMETO_QA_CONFIG = DatasetConfig(
     name="umimeto-qa",
-    pretty_name="the Czech knowledge dataset UmimetoQA",
-    huggingface_id="EuroEval/umimeto-qa",
+    pretty_name="Umimeto QA",
+    source="EuroEval/umimeto-qa",
     task=KNOW,
-    languages=[CS],
+    languages=[CZECH],
 )
 
 HELLASWAG_CS_CONFIG = DatasetConfig(
     name="hellaswag-cs",
-    pretty_name="the truncated version of the Czech common-sense reasoning dataset "
-    "HellaSwag-cs, translated from the English HellaSwag dataset",
-    huggingface_id="EuroEval/hellaswag-cs-mini",
+    pretty_name="HellaSwag-cs",
+    source="EuroEval/hellaswag-cs-mini",
     task=COMMON_SENSE,
-    languages=[CS],
+    languages=[CZECH],
 )
 
 
@@ -71,9 +67,9 @@ HELLASWAG_CS_CONFIG = DatasetConfig(
 
 SCALA_CS_CONFIG = DatasetConfig(
     name="scala-cs",
-    pretty_name="the Czech part of the linguistic acceptability dataset ScaLA",
-    huggingface_id="EuroEval/scala-cs",
+    pretty_name="ScaLA-cs",
+    source="EuroEval/scala-cs",
     task=LA,
-    languages=[CS],
+    languages=[CZECH],
     unofficial=True,
 )

euroeval/dataset_configs/danish.py

@@ -1,87 +1,81 @@
 """All Danish dataset configurations used in EuroEval."""
 
 from ..data_models import DatasetConfig
-from ..languages import DA
+from ..languages import DANISH
 from ..tasks import COMMON_SENSE, EUROPEAN_VALUES, KNOW, LA, MCRC, NER, RC, SENT, SUMM
 
 ### Official datasets ###
 
 ANGRY_TWEETS_CONFIG = DatasetConfig(
     name="angry-tweets",
-    pretty_name="the truncated version of the Danish sentiment classification "
-    "dataset AngryTweets",
-    huggingface_id="EuroEval/angry-tweets-mini",
+    pretty_name="AngryTweets",
+    source="EuroEval/angry-tweets-mini",
     task=SENT,
-    languages=[DA],
+    languages=[DANISH],
 )
 
 SCALA_DA_CONFIG = DatasetConfig(
     name="scala-da",
-    pretty_name="the Danish part of the linguistic acceptability dataset ScaLA",
-    huggingface_id="EuroEval/scala-da",
+    pretty_name="ScaLA-da",
+    source="EuroEval/scala-da",
     task=LA,
-    languages=[DA],
+    languages=[DANISH],
 )
 
 DANSK_CONFIG = DatasetConfig(
     name="dansk",
-    pretty_name="the truncated version of the Danish named entity recognition "
-    "dataset DANSK",
-    huggingface_id="EuroEval/dansk-mini",
+    pretty_name="DANSK",
+    source="EuroEval/dansk-mini",
     task=NER,
-    languages=[DA],
+    languages=[DANISH],
 )
 
 MULTI_WIKI_QA_DA_CONFIG = DatasetConfig(
     name="multi-wiki-qa-da",
-    pretty_name="the truncated version of the Danish part of the reading "
-    "comprehension dataset MultiWikiQA",
-    huggingface_id="EuroEval/multi-wiki-qa-da-mini",
+    pretty_name="MultiWikiQA-da",
+    source="EuroEval/multi-wiki-qa-da-mini",
     task=RC,
-    languages=[DA],
+    languages=[DANISH],
 )
 
 NORDJYLLAND_NEWS_CONFIG = DatasetConfig(
     name="nordjylland-news",
-    pretty_name="the truncated version of the Danish summarisation dataset "
-    "Nordjylland News",
-    huggingface_id="EuroEval/nordjylland-news-mini",
+    pretty_name="Nordjylland News",
+    source="EuroEval/nordjylland-news-mini",
     task=SUMM,
-    languages=[DA],
+    languages=[DANISH],
 )
 
 DANSKE_TALEMAADER_CONFIG = DatasetConfig(
     name="danske-talemaader",
-    pretty_name="the truncated version of the Danish knowledge dataset Danske "
-    "Talemåder",
-    huggingface_id="EuroEval/danske-talemaader",
+    pretty_name="Danske Talemåder",
+    source="EuroEval/danske-talemaader",
     task=KNOW,
-    languages=[DA],
+    languages=[DANISH],
 )
 
 DANISH_CITIZEN_TESTS_CONFIG = DatasetConfig(
     name="danish-citizen-tests",
-    pretty_name="the Danish knowledge dataset Danish Citizen Tests",
-    huggingface_id="EuroEval/danish-citizen-tests-updated",
+    pretty_name="Danish Citizen Tests",
+    source="EuroEval/danish-citizen-tests-updated",
     task=KNOW,
-    languages=[DA],
+    languages=[DANISH],
 )
 
 HELLASWAG_DA_CONFIG = DatasetConfig(
     name="hellaswag-da",
-    pretty_name="the truncated version of the Danish common-sense reasoning dataset "
-    "HellaSwag-da, translated from the English HellaSwag dataset",
-    huggingface_id="EuroEval/hellaswag-da-mini",
+    pretty_name="HellaSwag-da",
+    source="EuroEval/hellaswag-da-mini",
     task=COMMON_SENSE,
-    languages=[DA],
+    languages=[DANISH],
 )
 
-EUROPEAN_VALUES_DA_CONFIG = DatasetConfig(
-    name="european-values-da",
-    pretty_name="the Danish version of the European values evaluation dataset",
-    huggingface_id="EuroEval/european-values-da",
+VALEU_DA_CONFIG = DatasetConfig(
+    name="valeu-da",
+    pretty_name="ValEU-da",
+    source="EuroEval/european-values-da",
     task=EUROPEAN_VALUES,
-    languages=[DA],
+    languages=[DANISH],
     splits=["test"],
     bootstrap_samples=False,
 )
@@ -91,95 +85,64 @@ EUROPEAN_VALUES_DA_CONFIG = DatasetConfig(
 
 DANE_CONFIG = DatasetConfig(
     name="dane",
-    pretty_name="the truncated version of the Danish named entity recognition "
-    "dataset DaNE",
-    huggingface_id="EuroEval/dane-mini",
+    pretty_name="DaNE",
+    source="EuroEval/dane-mini",
     task=NER,
-    languages=[DA],
+    languages=[DANISH],
     unofficial=True,
 )
 
 MMLU_DA_CONFIG = DatasetConfig(
     name="mmlu-da",
-    pretty_name="the truncated version of the Danish knowledge dataset MMLU-da, "
-    "translated from the English MMLU dataset",
-    huggingface_id="EuroEval/mmlu-da-mini",
+    pretty_name="MMLU-da",
+    source="EuroEval/mmlu-da-mini",
     task=KNOW,
-    languages=[DA],
+    languages=[DANISH],
     unofficial=True,
 )
 
 ARC_DA_CONFIG = DatasetConfig(
     name="arc-da",
-    pretty_name="the truncated version of the Danish knowledge dataset ARC-da, "
-    "translated from the English ARC dataset",
-    huggingface_id="EuroEval/arc-da-mini",
+    pretty_name="ARC-da",
+    source="EuroEval/arc-da-mini",
     task=KNOW,
-    languages=[DA],
+    languages=[DANISH],
     unofficial=True,
 )
 
 BELEBELE_DA_CONFIG = DatasetConfig(
     name="belebele-da",
-    pretty_name="the Danish multiple choice reading comprehension dataset BeleBele-da, "
-    "translated from the English BeleBele dataset",
-    huggingface_id="EuroEval/belebele-da-mini",
+    pretty_name="Belebele-da",
+    source="EuroEval/belebele-da-mini",
     task=MCRC,
-    languages=[DA],
+    languages=[DANISH],
     unofficial=True,
 )
 
 SCANDIQA_DA_CONFIG = DatasetConfig(
     name="scandiqa-da",
-    pretty_name="the Danish part of the truncated version of the question answering "
-    "dataset ScandiQA",
-    huggingface_id="EuroEval/scandiqa-da-mini",
+    pretty_name="ScandiQA-da",
+    source="EuroEval/scandiqa-da-mini",
     task=RC,
-    languages=[DA],
+    languages=[DANISH],
     unofficial=True,
 )
 
 GOLDENSWAG_DA_CONFIG = DatasetConfig(
     name="goldenswag-da",
-    pretty_name="the truncated version of the Danish common-sense reasoning "
-    "dataset GoldenSwag-da, translated from the English GoldenSwag dataset",
-    huggingface_id="EuroEval/goldenswag-da-mini",
+    pretty_name="GoldenSwag-da",
+    source="EuroEval/goldenswag-da-mini",
     task=COMMON_SENSE,
-    languages=[DA],
+    languages=[DANISH],
     unofficial=True,
 )
 
 WINOGRANDE_DA_CONFIG = DatasetConfig(
     name="winogrande-da",
-    pretty_name="the Danish common-sense reasoning dataset Winogrande-da, translated "
-    "from the English Winogrande dataset",
-    huggingface_id="EuroEval/winogrande-da",
+    pretty_name="Winogrande-da",
+    source="EuroEval/winogrande-da",
     task=COMMON_SENSE,
-    languages=[DA],
+    languages=[DANISH],
     _labels=["a", "b"],
     unofficial=True,
 )
-
-EUROPEAN_VALUES_SITUATIONAL_DA_CONFIG = DatasetConfig(
-    name="european-values-situational-da",
-    pretty_name="the Danish version of the European values evaluation dataset, where "
-    "the questions are phrased in a situational way",
-    huggingface_id="EuroEval/european-values-situational-da",
-    task=EUROPEAN_VALUES,
-    languages=[DA],
-    splits=["test"],
-    bootstrap_samples=False,
-    unofficial=True,
-)
-
-EUROPEAN_VALUES_COMPLETIONS_DA_CONFIG = DatasetConfig(
-    name="european-values-completions-da",
-    pretty_name="the Danish version of the European values evaluation dataset, where "
-    "the questions are phrased as sentence completions",
-    huggingface_id="EuroEval/european-values-completions-da",
-    task=EUROPEAN_VALUES,
-    languages=[DA],
-    splits=["test"],
-    bootstrap_samples=False,
-    unofficial=True,
-)

euroeval/dataset_configs/dutch.py

@@ -1,80 +1,74 @@
 """All Dutch dataset configurations used in EuroEval."""
 
 from ..data_models import DatasetConfig
-from ..languages import NL
+from ..languages import DUTCH
 from ..tasks import COMMON_SENSE, EUROPEAN_VALUES, KNOW, LA, MCRC, NER, RC, SENT, SUMM
 
 ### Official datasets ###
 
 DBRD_CONFIG = DatasetConfig(
     name="dbrd",
-    pretty_name="the truncated version of the Dutch sentiment classification "
-    "dataset DBRD",
-    huggingface_id="EuroEval/dbrd-mini",
+    pretty_name="DBRD",
+    source="EuroEval/dbrd-mini",
     task=SENT,
-    languages=[NL],
+    languages=[DUTCH],
     _labels=["negative", "positive"],
 )
 
 SCALA_NL_CONFIG = DatasetConfig(
     name="scala-nl",
-    pretty_name="the Dutch part of the linguistic acceptability dataset ScaLA",
-    huggingface_id="EuroEval/scala-nl",
+    pretty_name="ScaLA-nl",
+    source="EuroEval/scala-nl",
     task=LA,
-    languages=[NL],
+    languages=[DUTCH],
 )
 
 CONLL_NL_CONFIG = DatasetConfig(
     name="conll-nl",
-    pretty_name="the Dutch part of the truncated version of the named entity "
-    "recognition dataset CoNLL 2002",
-    huggingface_id="EuroEval/conll-nl-mini",
+    pretty_name="CoNLL-nl",
+    source="EuroEval/conll-nl-mini",
     task=NER,
-    languages=[NL],
+    languages=[DUTCH],
 )
 
 SQUAD_NL_CONFIG = DatasetConfig(
     name="squad-nl",
-    pretty_name="the truncated version of the Dutch reading comprehension dataset "
-    "SQuAD-nl, translated from the English SQuAD dataset",
-    huggingface_id="EuroEval/squad-nl-v2-mini",
+    pretty_name="SQuAD-nl",
+    source="EuroEval/squad-nl-v2-mini",
     task=RC,
-    languages=[NL],
+    languages=[DUTCH],
 )
 
 WIKI_LINGUA_NL_CONFIG = DatasetConfig(
     name="wiki-lingua-nl",
-    pretty_name="the Dutch part of the truncated version of the summarisation dataset "
-    "WikiLingua",
-    huggingface_id="EuroEval/wiki-lingua-nl-mini",
+    pretty_name="WikiLingua-nl",
+    source="EuroEval/wiki-lingua-nl-mini",
     task=SUMM,
-    languages=[NL],
+    languages=[DUTCH],
 )
 
 MMLU_NL_CONFIG = DatasetConfig(
     name="mmlu-nl",
-    pretty_name="the truncated version of the Dutch knowledge dataset MMLU-nl, "
-    "translated from the English MMLU dataset",
-    huggingface_id="EuroEval/mmlu-nl-mini",
+    pretty_name="MMLU-nl",
+    source="EuroEval/mmlu-nl-mini",
     task=KNOW,
-    languages=[NL],
+    languages=[DUTCH],
 )
 
 HELLASWAG_NL_CONFIG = DatasetConfig(
     name="hellaswag-nl",
-    pretty_name="the truncated version of the Dutch common-sense reasoning dataset "
-    "HellaSwag-nl, translated from the English HellaSwag dataset",
-    huggingface_id="EuroEval/hellaswag-nl-mini",
+    pretty_name="HellaSwag-nl",
+    source="EuroEval/hellaswag-nl-mini",
     task=COMMON_SENSE,
-    languages=[NL],
+    languages=[DUTCH],
 )
 
-EUROPEAN_VALUES_NL_CONFIG = DatasetConfig(
-    name="european-values-nl",
-    pretty_name="the Dutch version of the European values evaluation dataset",
-    huggingface_id="EuroEval/european-values-nl",
+VALEU_NL_CONFIG = DatasetConfig(
+    name="valeu-nl",
+    pretty_name="VaLEU-nl",
+    source="EuroEval/european-values-nl",
     task=EUROPEAN_VALUES,
-    languages=[NL],
+    languages=[DUTCH],
     splits=["test"],
     bootstrap_samples=False,
     _instruction_prompt="{text}",
@@ -85,96 +79,64 @@ EUROPEAN_VALUES_NL_CONFIG = DatasetConfig(
 
 DUTCH_COLA_CONFIG = DatasetConfig(
     name="dutch-cola",
-    pretty_name="the truncated version of the Dutch linguistic acceptability dataset "
-    "Dutch CoLA",
-    huggingface_id="EuroEval/dutch-cola",
+    pretty_name="Dutch CoLA",
+    source="EuroEval/dutch-cola",
     task=LA,
-    languages=[NL],
+    languages=[DUTCH],
     unofficial=True,
 )
 
 DUTCH_COLA_FULL_CONFIG = DatasetConfig(
     name="dutch-cola-full",
-    pretty_name="the Dutch linguistic acceptability dataset Dutch CoLA",
-    huggingface_id="EuroEval/dutch-cola-full",
+    pretty_name="Dutch CoLA Full",
+    source="EuroEval/dutch-cola-full",
     task=LA,
-    languages=[NL],
+    languages=[DUTCH],
     unofficial=True,
 )
 
 ARC_NL_CONFIG = DatasetConfig(
     name="arc-nl",
-    pretty_name="the truncated version of the Dutch knowledge dataset ARC-nl, "
-    "translated from the English ARC dataset",
-    huggingface_id="EuroEval/arc-nl-mini",
+    pretty_name="ARC-nl",
+    source="EuroEval/arc-nl-mini",
     task=KNOW,
-    languages=[NL],
+    languages=[DUTCH],
     unofficial=True,
 )
 
 BELEBELE_NL_CONFIG = DatasetConfig(
     name="belebele-nl",
-    pretty_name="the Dutch multiple choice reading comprehension dataset BeleBele-nl, "
-    "translated from the English BeleBele dataset",
-    huggingface_id="EuroEval/belebele-nl-mini",
+    pretty_name="Belebele-nl",
+    source="EuroEval/belebele-nl-mini",
     task=MCRC,
-    languages=[NL],
+    languages=[DUTCH],
     unofficial=True,
 )
 
 MULTI_WIKI_QA_NL_CONFIG = DatasetConfig(
     name="multi-wiki-qa-nl",
-    pretty_name="the truncated version of the Dutch part of the reading "
-    "comprehension dataset MultiWikiQA",
-    huggingface_id="EuroEval/multi-wiki-qa-nl-mini",
+    pretty_name="MultiWikiQA-nl",
+    source="EuroEval/multi-wiki-qa-nl-mini",
     task=RC,
-    languages=[NL],
+    languages=[DUTCH],
     unofficial=True,
 )
 
 GOLDENSWAG_NL_CONFIG = DatasetConfig(
     name="goldenswag-nl",
-    pretty_name="the truncated version of the Dutch common-sense reasoning "
-    "dataset GoldenSwag-nl, translated from the English GoldenSwag dataset",
-    huggingface_id="EuroEval/goldenswag-nl-mini",
+    pretty_name="GoldenSwag-nl",
+    source="EuroEval/goldenswag-nl-mini",
     task=COMMON_SENSE,
-    languages=[NL],
+    languages=[DUTCH],
     unofficial=True,
 )
 
 WINOGRANDE_NL_CONFIG = DatasetConfig(
     name="winogrande-nl",
-    pretty_name="the Dutch common-sense reasoning dataset Winogrande-nl, translated "
-    "from the English Winogrande dataset",
-    huggingface_id="EuroEval/winogrande-nl",
+    pretty_name="Winogrande-nl",
+    source="EuroEval/winogrande-nl",
     task=COMMON_SENSE,
-    languages=[NL],
+    languages=[DUTCH],
     _labels=["a", "b"],
     unofficial=True,
 )
-
-EUROPEAN_VALUES_SITUATIONAL_NL_CONFIG = DatasetConfig(
-    name="european-values-situational-nl",
-    pretty_name="the Dutch version of the European values evaluation dataset, where "
-    "the questions are phrased in a situational way",
-    huggingface_id="EuroEval/european-values-situational-nl",
-    task=EUROPEAN_VALUES,
-    languages=[NL],
-    splits=["test"],
-    bootstrap_samples=False,
-    _instruction_prompt="{text}",
-    unofficial=True,
-)
-
-EUROPEAN_VALUES_COMPLETIONS_NL_CONFIG = DatasetConfig(
-    name="european-values-completions-nl",
-    pretty_name="the Dutch version of the European values evaluation dataset, where "
-    "the questions are phrased as sentence completions",
-    huggingface_id="EuroEval/european-values-completions-nl",
-    task=EUROPEAN_VALUES,
-    languages=[NL],
-    splits=["test"],
-    bootstrap_samples=False,
-    _instruction_prompt="{text}",
-    unofficial=True,
-)