EuroEval 15.10.1__py3-none-any.whl → 15.12.0__py3-none-any.whl

euroeval/tasks.py

@@ -1,6 +1,7 @@
 """All benchmarks tasks used in EuroEval."""
 
-from .data_models import MetricConfig, Task
+from . import metrics as m
+from .data_models import Task
 from .enums import TaskGroup
 from .prompt_templates import (
     LA_TEMPLATES,
@@ -25,21 +26,7 @@ LA = Task(
     name="linguistic-acceptability",
     task_group=TaskGroup.SEQUENCE_CLASSIFICATION,
     template_dict=LA_TEMPLATES,
-    metrics=[
-        MetricConfig(
-            name="mcc",
-            pretty_name="Matthew's Correlation Coefficient",
-            huggingface_id="matthews_correlation",
-            results_key="matthews_correlation",
-        ),
-        MetricConfig(
-            name="macro_f1",
-            pretty_name="Macro-average F1-score",
-            huggingface_id="f1",
-            results_key="f1",
-            compute_kwargs=dict(average="macro"),
-        ),
-    ],
+    metrics=[m.mcc_metric, m.macro_f1_metric],
     default_num_few_shot_examples=12,
     default_max_generated_tokens=5,
     default_labels=["correct", "incorrect"],
@@ -50,20 +37,7 @@ NER = Task(
     name="named-entity-recognition",
     task_group=TaskGroup.TOKEN_CLASSIFICATION,
     template_dict=NER_TEMPLATES,
-    metrics=[
-        MetricConfig(
-            name="micro_f1_no_misc",
-            pretty_name="Micro-average F1-score without MISC tags",
-            huggingface_id="seqeval",
-            results_key="overall_f1",
-        ),
-        MetricConfig(
-            name="micro_f1",
-            pretty_name="Micro-average F1-score with MISC tags",
-            huggingface_id="seqeval",
-            results_key="overall_f1",
-        ),
-    ],
+    metrics=[m.micro_f1_no_misc_metric, m.micro_f1_metric],
     default_num_few_shot_examples=8,
     default_max_generated_tokens=128,
     default_labels=[
@@ -84,22 +58,7 @@ RC = Task(
     name="reading-comprehension",
     task_group=TaskGroup.QUESTION_ANSWERING,
     template_dict=RC_TEMPLATES,
-    metrics=[
-        MetricConfig(
-            name="f1",
-            pretty_name="F1-score",
-            huggingface_id="squad_v2",
-            results_key="f1",
-            postprocessing_fn=lambda raw_score: (raw_score, f"{raw_score:.2f}%"),
-        ),
-        MetricConfig(
-            name="em",
-            pretty_name="Exact Match",
-            huggingface_id="squad_v2",
-            results_key="exact",
-            postprocessing_fn=lambda raw_score: (raw_score, f"{raw_score:.2f}%"),
-        ),
-    ],
+    metrics=[m.f1_metric, m.em_metric],
     default_num_few_shot_examples=4,
     default_max_generated_tokens=32,
     default_labels=["start_positions", "end_positions"],
@@ -110,21 +69,7 @@ SENT = Task(
     name="sentiment-classification",
     task_group=TaskGroup.SEQUENCE_CLASSIFICATION,
     template_dict=SENT_TEMPLATES,
-    metrics=[
-        MetricConfig(
-            name="mcc",
-            pretty_name="Matthew's Correlation Coefficient",
-            huggingface_id="matthews_correlation",
-            results_key="matthews_correlation",
-        ),
-        MetricConfig(
-            name="macro_f1",
-            pretty_name="Macro-average F1-score",
-            huggingface_id="f1",
-            results_key="f1",
-            compute_kwargs=dict(average="macro"),
-        ),
-    ],
+    metrics=[m.mcc_metric, m.macro_f1_metric],
     default_num_few_shot_examples=12,
     default_max_generated_tokens=5,
     default_labels=["positive", "neutral", "negative"],
@@ -135,23 +80,7 @@ SUMM = Task(
     name="summarization",
     task_group=TaskGroup.TEXT_TO_TEXT,
     template_dict=SUMM_TEMPLATES,
-    metrics=[
-        MetricConfig(
-            name="bertscore",
-            pretty_name="BERTScore",
-            huggingface_id="bertscore",
-            results_key="f1",
-            compute_kwargs=dict(
-                model_type="microsoft/mdeberta-v3-base", device="auto", batch_size=1
-            ),
-        ),
-        MetricConfig(
-            name="rouge_l",
-            pretty_name="ROUGE-L",
-            huggingface_id="rouge",
-            results_key="rougeL",
-        ),
-    ],
+    metrics=[m.bert_score_metric, m.rouge_l_metric],
     default_num_few_shot_examples=1,
     default_max_generated_tokens=256,
     default_labels=[],
@@ -162,20 +91,7 @@ KNOW = Task(
     name="knowledge",
     task_group=TaskGroup.MULTIPLE_CHOICE_CLASSIFICATION,
     template_dict=MULTIPLE_CHOICE_TEMPLATES,
-    metrics=[
-        MetricConfig(
-            name="mcc",
-            pretty_name="Matthew's Correlation Coefficient",
-            huggingface_id="matthews_correlation",
-            results_key="matthews_correlation",
-        ),
-        MetricConfig(
-            name="accuracy",
-            pretty_name="Accuracy",
-            huggingface_id="accuracy",
-            results_key="accuracy",
-        ),
-    ],
+    metrics=[m.mcc_metric, m.accuracy_metric],
     default_num_few_shot_examples=5,
     default_max_generated_tokens=5,
     default_labels=["a", "b", "c", "d"],
@@ -186,20 +102,7 @@ MCRC = Task(
     name="multiple-choice-reading-comprehension",
     task_group=TaskGroup.MULTIPLE_CHOICE_CLASSIFICATION,
     template_dict=MULTIPLE_CHOICE_TEMPLATES,
-    metrics=[
-        MetricConfig(
-            name="mcc",
-            pretty_name="Matthew's Correlation Coefficient",
-            huggingface_id="matthews_correlation",
-            results_key="matthews_correlation",
-        ),
-        MetricConfig(
-            name="accuracy",
-            pretty_name="Accuracy",
-            huggingface_id="accuracy",
-            results_key="accuracy",
-        ),
-    ],
+    metrics=[m.mcc_metric, m.accuracy_metric],
     default_num_few_shot_examples=5,
     default_max_generated_tokens=5,
     default_labels=["a", "b", "c", "d"],
@@ -210,20 +113,7 @@ COMMON_SENSE = Task(
     name="common-sense-reasoning",
     task_group=TaskGroup.MULTIPLE_CHOICE_CLASSIFICATION,
     template_dict=MULTIPLE_CHOICE_TEMPLATES,
-    metrics=[
-        MetricConfig(
-            name="mcc",
-            pretty_name="Matthew's Correlation Coefficient",
-            huggingface_id="matthews_correlation",
-            results_key="matthews_correlation",
-        ),
-        MetricConfig(
-            name="accuracy",
-            pretty_name="Accuracy",
-            huggingface_id="accuracy",
-            results_key="accuracy",
-        ),
-    ],
+    metrics=[m.mcc_metric, m.accuracy_metric],
     default_num_few_shot_examples=5,
     default_max_generated_tokens=5,
     default_labels=["a", "b", "c", "d"],
@@ -234,22 +124,7 @@ SPEED = Task(
     name="speed",
     task_group=TaskGroup.SPEED,
     template_dict={},
-    metrics=[
-        MetricConfig(
-            name="speed",
-            pretty_name="Tokens per second",
-            huggingface_id="",
-            results_key="speed",
-            postprocessing_fn=lambda raw_score: (raw_score, f"{raw_score:,.0f}"),
-        ),
-        MetricConfig(
-            name="speed_short",
-            pretty_name="Tokens per second on short documents",
-            huggingface_id="",
-            results_key="speed",
-            postprocessing_fn=lambda raw_score: (raw_score, f"{raw_score:,.0f}"),
-        ),
-    ],
+    metrics=[m.speed_metric, m.speed_short_metric],
     default_num_few_shot_examples=0,
     default_max_generated_tokens=5,
     default_labels=[],

euroeval/types.py

@@ -2,16 +2,17 @@
 
 import typing as t
 
-from numpy.typing import NDArray
 from transformers.trainer_utils import EvalPrediction
 
 if t.TYPE_CHECKING:
+    from numpy.typing import NDArray
+
     from .data_models import GenerativeModelOutput
 
 
 ScoreDict: t.TypeAlias = dict[str, dict[str, float] | list[dict[str, float]]]
-Predictions: t.TypeAlias = NDArray | list[str] | list[list[str]]
-Labels: t.TypeAlias = NDArray | list[str] | list[list[str]]
+Predictions: t.TypeAlias = "NDArray | list[str] | list[list[str]]"
+Labels: t.TypeAlias = "NDArray | list[str] | list[list[str]]"
 
 
 class ComputeMetricsFunction(t.Protocol):
@@ -21,7 +22,8 @@ class ComputeMetricsFunction(t.Protocol):
         self,
         model_outputs_and_labels: EvalPrediction
         | tuple[
-            NDArray | list[str] | list[list[str]], NDArray | list[str] | list[list[str]]
+            "NDArray | list[str] | list[list[str]]",
+            "NDArray | list[str] | list[list[str]]",
         ],
     ) -> dict[str, float]:
         """Compute the metrics.

{euroeval-15.10.1.dist-info → euroeval-15.12.0.dist-info}/METADATA

@@ -1,14 +1,14 @@
 Metadata-Version: 2.4
 Name: EuroEval
-Version: 15.10.1
+Version: 15.12.0
 Summary: The robust European language model benchmark.
 Project-URL: Repository, https://github.com/EuroEval/EuroEval
 Project-URL: Issues, https://github.com/EuroEval/EuroEval/issues
-Author-email: Dan Saattrup Nielsen <dan.nielsen@alexandra.dk>
-Maintainer-email: Dan Saattrup Nielsen <dan.nielsen@alexandra.dk>
+Author-email: Dan Saattrup Smart <dan.smart@alexandra.dk>
+Maintainer-email: Dan Saattrup Smart <dan.smart@alexandra.dk>
 License: MIT License
         
-        Copyright (c) 2022-2024 Dan Saattrup Nielsen
+        Copyright (c) 2022-2025 Dan Saattrup Smart
         
         Permission is hereby granted, free of charge, to any person obtaining a copy
         of this software and associated documentation files (the "Software"), to deal
@@ -43,6 +43,7 @@ Requires-Dist: numpy<2.0.0,>=1.23.0
 Requires-Dist: ollama>=0.5.1
 Requires-Dist: pandas>=2.2.0
 Requires-Dist: peft>=0.15.0
+Requires-Dist: protobuf>=2.0.0
 Requires-Dist: pydantic>=2.6.0
 Requires-Dist: pyinfer>=0.0.3
 Requires-Dist: python-dotenv>=1.0.1
@@ -94,8 +95,7 @@ ______________________________________________________________________
 
 ## Maintainer
 
-- Dan Saattrup Nielsen ([@saattrupdan](https://github.com/saattrupdan),
-  dan.nielsen@alexandra.dk)
+- Dan Saattrup Smart ([@saattrupdan](https://github.com/saattrupdan), dan.smart@alexandra.dk)
 
 
 ## Installation
@@ -268,14 +268,14 @@ contributing new datasets, your help makes this project better for everyone.
 If you want to cite the framework then feel free to use this:
 
 ```
-@article{nielsen2024encoder,
+@article{smart2024encoder,
   title={Encoder vs Decoder: Comparative Analysis of Encoder and Decoder Language Models on Multilingual NLU Tasks},
-  author={Nielsen, Dan Saattrup and Enevoldsen, Kenneth and Schneider-Kamp, Peter},
+  author={Smart, Dan Saattrup and Enevoldsen, Kenneth and Schneider-Kamp, Peter},
   journal={arXiv preprint arXiv:2406.13469},
   year={2024}
 }
-@inproceedings{nielsen2023scandeval,
-  author = {Nielsen, Dan Saattrup},
+@inproceedings{smart2023scandeval,
+  author = {Smart, Dan Saattrup},
   booktitle = {Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)},
   month = may,
   pages = {185--201},

euroeval-15.12.0.dist-info/RECORD

@@ -0,0 +1,63 @@
+euroeval/__init__.py,sha256=fZyR9R3C3vwGJS3CrCJ6ySr_FDnMu_Aqnz0FdadWEEs,3399
+euroeval/benchmark_config_factory.py,sha256=jKC8bEzJSGGCcG8aWsPxiyHX6fjOQYQWvkp1MIUuHYM,11564
+euroeval/benchmarker.py,sha256=SDBzdCa4I8u1XDeN_1mKTFzfaaQbbY_oWcHt3niADxk,48497
+euroeval/callbacks.py,sha256=5BTlDvBJ60xRvj01EpXZSZu3MFdKa3LgVuhxoLb3i3E,2565
+euroeval/cli.py,sha256=h81Lswm_q9htkYz-GQQQVIsdsUPnfe3LDH8AZdBcpKs,8602
+euroeval/constants.py,sha256=0KHrH74zGM8vNF4uZG_a5qFJRZH5YgyQULYZtCKlo68,2452
+euroeval/data_loading.py,sha256=DP-cqwN_d0Y-KaN8P8c3fDr6PX80UYROHgRwX82ix4w,4156
+euroeval/data_models.py,sha256=gPHyIoN2A5_O-cJgyb6jhn6enH8zsiIBI09W_wdHMQs,22031
+euroeval/enums.py,sha256=L9LcNeruuhHvze9vKRogXY9vonRzoBqDzWSP6hxKQ7A,3195
+euroeval/exceptions.py,sha256=5kQ-YvHyFO3aaA-zfOTaS07LRFH8xlSqlOiATvnIObY,5116
+euroeval/finetuning.py,sha256=BrPZ-6qFY8K-dwfaRwNetVYfYburoQwLQty6pn6iP_s,11340
+euroeval/generation.py,sha256=1fqFEWwM2RzI3uPZem95VFWbN8EfrKZQTrHEP34ihHs,11622
+euroeval/generation_utils.py,sha256=zRsaOHcbhysbMa983BZXxfd-qMe4NYts-ZbQxfvNTK4,13310
+euroeval/human_evaluation.py,sha256=Jtz3K5Lqne48wPZWf4EAd3d-n_wX27nGJHigjhV1D7s,27537
+euroeval/languages.py,sha256=cr_Z5jtaHb2XY0zeOhuk3ATHX74PODzt6gMPC2zMD7c,8594
+euroeval/metrics.py,sha256=nxosyoRjlk7TcoAOkjU7zx2TB43b9tA8M1m4V1s5eKU,15516
+euroeval/model_cache.py,sha256=HgXTgn4RMBqIjKaTmYzxu0f4NIwbXx1XJFbvbITqy4E,8686
+euroeval/model_config.py,sha256=64KKHPTrpsFhFAANtBnAKkOs7PWZ50GXkXeDl4jICgs,2748
+euroeval/model_loading.py,sha256=B6dyjYO0Dg7NOcUXls8Sjwe6W0c2UqJ1OGw-RkzoSSQ,2239
+euroeval/scores.py,sha256=TatSbjia7Zwj71gQFyV_gCHyppMbOgeaZgNCib8G86k,2849
+euroeval/speed_benchmark.py,sha256=6bFGeMmtdl_6owkxNQ3ZKiyQQS58k0NApzlsbDgBW5s,4037
+euroeval/tasks.py,sha256=btxf29M5rUP7JjBl6u9aQlHQAxrJNP4bRbdEQtDnmDA,3376
+euroeval/tokenization_utils.py,sha256=LxgGs7juS5PuMYt5LL2X6eVXdtnpi-A2jFxqcWpF6NA,17931
+euroeval/types.py,sha256=EIYMNOqqHqibnbNw-fvdst6HwTvq32gtxhr7jL7i-xM,2511
+euroeval/utils.py,sha256=5R7y67xe0ODaje7k8nOu2AFS3Ph2gcsiWpIq5rjSSuA,11613
+euroeval/benchmark_modules/__init__.py,sha256=TNO-sNDwlXE-LMFXfwwqjQqUy55gywSmwRBcoPUFuaU,236
+euroeval/benchmark_modules/base.py,sha256=D1oKD16KBvxEoBUfqwvzvcDc1hx6letdD3v1PnBmF4A,10669
+euroeval/benchmark_modules/fresh.py,sha256=sg_AXNPApFObCzCRWhCgKxfr-eqQsT6Ri0xx0_Yy5JM,10293
+euroeval/benchmark_modules/hf.py,sha256=-W_bWEdm0zePkn4nDz4l0T4hhJJnlfwHrtIO3m5BrUs,44725
+euroeval/benchmark_modules/litellm.py,sha256=_gKBbJsXzo_cHJVaeuQpHRBENEZUGS_vcC-uGIhhmHA,52111
+euroeval/benchmark_modules/vllm.py,sha256=kq3PMUuRT0NOky6XSHl1JeHTDGehwcub0HcGC5S_Wv4,38834
+euroeval/dataset_configs/__init__.py,sha256=EbjEyHwBtSztASl8_xblD8hessruDdV4Eg1vXrmGOuY,1935
+euroeval/dataset_configs/danish.py,sha256=MTt9EcriSer0QaFQ7_6evYxh-g9OPjroWegYdFpiKag,3395
+euroeval/dataset_configs/dutch.py,sha256=r21nxEvMmBkKqPXVW082batPsxJ9d0RB4DzngOTMJSk,3185
+euroeval/dataset_configs/english.py,sha256=1q8XJqIVWBBNkldL7t-cVnU2O9EUb9_xoVRSN8arN90,2561
+euroeval/dataset_configs/faroese.py,sha256=QQgLe5gv0f3AtXe5rV65xZ98gFgyITQPDr3UwO4Bnv4,1350
+euroeval/dataset_configs/finnish.py,sha256=_8YWIlZNpO8Qi233bH7cKwm3tq3WETLfC_6mzg7LLog,2045
+euroeval/dataset_configs/french.py,sha256=ATsj8_9_GxFTQgmfrniPQFZ1R9hoQCI1_ieWTnscFHU,2382
+euroeval/dataset_configs/german.py,sha256=QO6PrBQY6kyZeQMU1vg6KrC_sKyj9U2ukS9nbKO19is,2560
+euroeval/dataset_configs/icelandic.py,sha256=mncl7X4yO9gBmYqXMBfm7FKU1jcKryerSgd0dqlIA_4,4198
+euroeval/dataset_configs/italian.py,sha256=KNjCvTzsEqH_EEk3At8slKqNwWWiIdbv_t5ke7n9nZI,2660
+euroeval/dataset_configs/norwegian.py,sha256=30YGdDPtDszG10BNDVHb-XXTGgGIIgDUNGoeM9q0K_E,5385
+euroeval/dataset_configs/portuguese.py,sha256=-HSDsujWfK__nV2SCu-z0ne0AXLDszOT05oYphQUDTw,2063
+euroeval/dataset_configs/spanish.py,sha256=Yzm1kiilEKoHyd3xD2wrw596Ac9UcaWhlE93GlOFjlc,2558
+euroeval/dataset_configs/swedish.py,sha256=SOD2nKQTVwTpTvr362mDPHon42kr9vWs5C0mK02Fh-o,2811
+euroeval/prompt_templates/__init__.py,sha256=HWMZpybxs2xHPnVeJ43893conARahIVLWNXeRhXEGZw,357
+euroeval/prompt_templates/linguistic_acceptability.py,sha256=ZN71BEt4HAhSYY-GWjh-S-iVvq5AODQJThkrjDhy4oM,7138
+euroeval/prompt_templates/multiple_choice.py,sha256=F9ItGQtnaaez15A8MQ1UCpKRDsLM-AZyRdYetGAofa0,5494
+euroeval/prompt_templates/named_entity_recognition.py,sha256=ga21s9T4_Hhbf88boWm7gnL7OgD7txuS_EeDgXaxEoE,13602
+euroeval/prompt_templates/reading_comprehension.py,sha256=yLqryWQAW04GULz_EyNDLOS7ZrDUeasuLFt-dtqCnYk,6585
+euroeval/prompt_templates/sentiment_classification.py,sha256=2Xsmj8lbaAXACHhwbbR4dWhoKyKB87TqpMO-ssQ-Djo,7649
+euroeval/prompt_templates/summarization.py,sha256=I98LlUOBVa_xo02npq7BWKKZOXGqm-_15i64QzbEsb0,5334
+euroeval/task_group_utils/__init__.py,sha256=CorGVkixkoEDOQuDsrOGlTmF1zmM0wnGHs8psWTfD28,72
+euroeval/task_group_utils/multiple_choice_classification.py,sha256=yfy8lczpZ_MY-Y4FQx3Et9vEUpuD3YMFjF3wQGCfMNw,6632
+euroeval/task_group_utils/question_answering.py,sha256=agwtWOmctgat98yqgFiMSPY6zmoaPgYVyzMmOkNjr58,27284
+euroeval/task_group_utils/sequence_classification.py,sha256=igmD24aMNN7QBJ8NDzgEnGwM-jq_zhC37QxazNm7GZ4,12711
+euroeval/task_group_utils/text_to_text.py,sha256=xOpja-W4E-1peMjZX8G-3G5iRgmFHHygrQ5WN1hB3FI,4550
+euroeval/task_group_utils/token_classification.py,sha256=wCy3aI-Sn9f-87tHzAnYDA6EbY3ah3xao1SnfnoRNz4,17490
+euroeval-15.12.0.dist-info/METADATA,sha256=8cY6HWgAZgrCkIA20lVKuf42y-e7U1MZQZSTdF3e7ig,13479
+euroeval-15.12.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+euroeval-15.12.0.dist-info/entry_points.txt,sha256=tKQRxN0HX2mGtbZbZQdCRFUDZIecA_z4mZduueor3Ug,135
+euroeval-15.12.0.dist-info/licenses/LICENSE,sha256=guvz_zBHgkQSY_QiUU0Bkc1k-L_PFZuLjIPfuKne2OY,1080
+euroeval-15.12.0.dist-info/RECORD,,

{euroeval-15.10.1.dist-info → euroeval-15.12.0.dist-info}/licenses/LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2022-2024 Dan Saattrup Nielsen
+Copyright (c) 2022-2025 Dan Saattrup Smart
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

euroeval-15.10.1.dist-info/RECORD

@@ -1,61 +0,0 @@
-euroeval/__init__.py,sha256=jjInLLkd5IrDrwqag3U35g7SgzITBlFYllgofc-uQFg,3067
-euroeval/benchmark_config_factory.py,sha256=icTeT5C-bNCJmvSWFlxKdEpRboZN8OjwaHGu7JM-2xI,11158
-euroeval/benchmarker.py,sha256=wmgrYVS31PMhhrVienjaVHHyfnZAy51kUvC6OjooiOw,48047
-euroeval/callbacks.py,sha256=F1AJCLB8FJpxqYprwLi_PsH4Bc0x4lyR8UiTG-GlFLY,2452
-euroeval/cli.py,sha256=d8JztMi_RbpUlEBXidd6DQ-xeC-xhozf_qU6Vkzye20,8161
-euroeval/constants.py,sha256=0KHrH74zGM8vNF4uZG_a5qFJRZH5YgyQULYZtCKlo68,2452
-euroeval/data_loading.py,sha256=2rMLSy8pbntlwmImizMtkTiUzj93mcv5kzYjZELWWfU,4081
-euroeval/data_models.py,sha256=7nAGDpN58Y35Lt9JZE_y0y5iOYesw2htcwHc68MkBZU,22953
-euroeval/enums.py,sha256=L9LcNeruuhHvze9vKRogXY9vonRzoBqDzWSP6hxKQ7A,3195
-euroeval/exceptions.py,sha256=5kQ-YvHyFO3aaA-zfOTaS07LRFH8xlSqlOiATvnIObY,5116
-euroeval/finetuning.py,sha256=OFS8YlDhckPupoKWf26Nrd7CTtLQzJXTsDvzMdSR_34,11319
-euroeval/generation.py,sha256=LSsskfLjIJ-c3gQxmr7eiAobPOm-5bU9vnR7uHQ7XmU,10745
-euroeval/generation_utils.py,sha256=zRsaOHcbhysbMa983BZXxfd-qMe4NYts-ZbQxfvNTK4,13310
-euroeval/human_evaluation.py,sha256=zqbbJkqm2Uymf-88PxM3R9vVRR8SZJlq3QrqWEoiVeE,27643
-euroeval/languages.py,sha256=LerXuRBAUYkQL6qSV-F82itAE4EgBGFBtzaGnJJZvOE,8555
-euroeval/model_cache.py,sha256=HgXTgn4RMBqIjKaTmYzxu0f4NIwbXx1XJFbvbITqy4E,8686
-euroeval/model_config.py,sha256=64KKHPTrpsFhFAANtBnAKkOs7PWZ50GXkXeDl4jICgs,2748
-euroeval/model_loading.py,sha256=B6dyjYO0Dg7NOcUXls8Sjwe6W0c2UqJ1OGw-RkzoSSQ,2239
-euroeval/scores.py,sha256=TovjCZD8wmGrIjA4v5oAQp18P5KVcHvakkByDh0Hstk,3059
-euroeval/speed_benchmark.py,sha256=J7VKWMf7GU_l0lRR8f0QeUr_vAaBQqTbgQ_yToHhp_0,3980
-euroeval/tasks.py,sha256=87gbe__K5KNIb1aBSuwGnMPmZgamJFecNNYmNgMxaVo,7069
-euroeval/tokenization_utils.py,sha256=LxgGs7juS5PuMYt5LL2X6eVXdtnpi-A2jFxqcWpF6NA,17931
-euroeval/types.py,sha256=E0JhLfg-ek5pdFcYJbnGRUSodHxkuR3o8XGuIrBcuRM,2485
-euroeval/utils.py,sha256=5R7y67xe0ODaje7k8nOu2AFS3Ph2gcsiWpIq5rjSSuA,11613
-euroeval/benchmark_modules/__init__.py,sha256=TNO-sNDwlXE-LMFXfwwqjQqUy55gywSmwRBcoPUFuaU,236
-euroeval/benchmark_modules/base.py,sha256=LcG46I2O5wcvu_3T_irBY6VkUhWVPKifBhcP-ln93TA,10798
-euroeval/benchmark_modules/fresh.py,sha256=_LWmpqiNGGTA-NoVC0v3-fS1sraDS9n-pgKUzz89jVk,9919
-euroeval/benchmark_modules/hf.py,sha256=Nbtn5eZ4axbmL09M8dGZCBr07pn9-btbqGgQ6q7KbHg,44620
-euroeval/benchmark_modules/litellm.py,sha256=LS4mBXXG6h4uJwySPc6SI6f0y_HuiKE7IprprqWpoCI,50601
-euroeval/benchmark_modules/vllm.py,sha256=sgeltOVfZA9bu0AmXV7PtZvuRst0I8s6VOIp0CI6DO8,38880
-euroeval/dataset_configs/__init__.py,sha256=kWKtlSAOY-olOQL3UtFqL6I3Tki3G3waMZSd2YChjCg,1895
-euroeval/dataset_configs/danish.py,sha256=MTt9EcriSer0QaFQ7_6evYxh-g9OPjroWegYdFpiKag,3395
-euroeval/dataset_configs/dutch.py,sha256=r21nxEvMmBkKqPXVW082batPsxJ9d0RB4DzngOTMJSk,3185
-euroeval/dataset_configs/english.py,sha256=-N85DiNVrZFqpahNUTfxaWy4vvdOWC8Bi0G4uAO4uDw,2326
-euroeval/dataset_configs/faroese.py,sha256=QQgLe5gv0f3AtXe5rV65xZ98gFgyITQPDr3UwO4Bnv4,1350
-euroeval/dataset_configs/finnish.py,sha256=_8YWIlZNpO8Qi233bH7cKwm3tq3WETLfC_6mzg7LLog,2045
-euroeval/dataset_configs/french.py,sha256=ATsj8_9_GxFTQgmfrniPQFZ1R9hoQCI1_ieWTnscFHU,2382
-euroeval/dataset_configs/german.py,sha256=QO6PrBQY6kyZeQMU1vg6KrC_sKyj9U2ukS9nbKO19is,2560
-euroeval/dataset_configs/icelandic.py,sha256=mncl7X4yO9gBmYqXMBfm7FKU1jcKryerSgd0dqlIA_4,4198
-euroeval/dataset_configs/italian.py,sha256=KNjCvTzsEqH_EEk3At8slKqNwWWiIdbv_t5ke7n9nZI,2660
-euroeval/dataset_configs/norwegian.py,sha256=2SD5681gZFa1Ig-AEpnyStbivan_bq_Pada4qwE7tw0,5181
-euroeval/dataset_configs/spanish.py,sha256=NviL-FzJ5jq1bLTRvbtZBiGrAmZjxyijZNpKZFrnT-M,2527
-euroeval/dataset_configs/swedish.py,sha256=SOD2nKQTVwTpTvr362mDPHon42kr9vWs5C0mK02Fh-o,2811
-euroeval/prompt_templates/__init__.py,sha256=HWMZpybxs2xHPnVeJ43893conARahIVLWNXeRhXEGZw,357
-euroeval/prompt_templates/linguistic_acceptability.py,sha256=FAIJKS26EVRxlLHk1C3lN0GDtd5AM0MwvaMf-NNIxfU,6677
-euroeval/prompt_templates/multiple_choice.py,sha256=6iEqiPpT-3WJN_gsyhyapnwsrcsYGdVkSkzwn-VKKxw,5101
-euroeval/prompt_templates/named_entity_recognition.py,sha256=Xd6gBJD2e1l8-We2Ujor7crRUBcbgnNeeVknBIrTMJo,12737
-euroeval/prompt_templates/reading_comprehension.py,sha256=yLqryWQAW04GULz_EyNDLOS7ZrDUeasuLFt-dtqCnYk,6585
-euroeval/prompt_templates/sentiment_classification.py,sha256=LDOwjGQ2kqhwgNyphPywQeolwNB09o-xYWc9RUbzc84,7136
-euroeval/prompt_templates/summarization.py,sha256=mcWeKNhGWmp7IG_iY64T-VOSabQg5wKddjSbJNYFDp8,4984
-euroeval/task_group_utils/__init__.py,sha256=CorGVkixkoEDOQuDsrOGlTmF1zmM0wnGHs8psWTfD28,72
-euroeval/task_group_utils/multiple_choice_classification.py,sha256=LQ6zD1UGi-jGCKI2xUJiQdAXoqb5QMpIJu41B2U0HPw,6543
-euroeval/task_group_utils/question_answering.py,sha256=D4oJL2vQEjHghyxiiiq_vj1IQC6eryqNoLXuTiQEPmw,28071
-euroeval/task_group_utils/sequence_classification.py,sha256=zwRUgVHqLlREILwyg-yuDPkrIQOfqGVPsFBai-2D9a8,13525
-euroeval/task_group_utils/text_to_text.py,sha256=Nu1_qRPLbboCd9Q5rxqY4fQFJ_aGXu80aWQqoTG1cYc,5047
-euroeval/task_group_utils/token_classification.py,sha256=3idWB81Fcx9UhTuk-gxMfXENrCBmiWBDUWdULXoIhpw,17863
-euroeval-15.10.1.dist-info/METADATA,sha256=mx7pTjlWwRsDgD05msa6lNaaq7M2XeoCQV-BxDLSvag,13472
-euroeval-15.10.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-euroeval-15.10.1.dist-info/entry_points.txt,sha256=tKQRxN0HX2mGtbZbZQdCRFUDZIecA_z4mZduueor3Ug,135
-euroeval-15.10.1.dist-info/licenses/LICENSE,sha256=oZp5fpOSQ7w-vFui8QNwrBIosrO7cnpArItdbvn52Ao,1082
-euroeval-15.10.1.dist-info/RECORD,,