EuroEval 16.2.1__tar.gz → 16.3.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of EuroEval might be problematic. Click here for more details.

Files changed (282) hide show
  1. {euroeval-16.2.1 → euroeval-16.3.0}/.github/ISSUE_TEMPLATE/benchmark_dataset_request.yaml +7 -2
  2. {euroeval-16.2.1 → euroeval-16.3.0}/.github/ISSUE_TEMPLATE/bug.yaml +6 -3
  3. {euroeval-16.2.1 → euroeval-16.3.0}/.github/ISSUE_TEMPLATE/feature_request.yaml +3 -1
  4. {euroeval-16.2.1 → euroeval-16.3.0}/.github/ISSUE_TEMPLATE/model_evaluation_request.yaml +3 -2
  5. euroeval-16.3.0/.markdownlint.jsonc +10 -0
  6. {euroeval-16.2.1 → euroeval-16.3.0}/.pre-commit-config.yaml +8 -2
  7. {euroeval-16.2.1 → euroeval-16.3.0}/CHANGELOG.md +561 -215
  8. {euroeval-16.2.1 → euroeval-16.3.0}/CODE_OF_CONDUCT.md +3 -3
  9. {euroeval-16.2.1 → euroeval-16.3.0}/CONTRIBUTING.md +6 -5
  10. {euroeval-16.2.1 → euroeval-16.3.0}/NEW_DATASET_GUIDE.md +48 -25
  11. {euroeval-16.2.1 → euroeval-16.3.0}/PKG-INFO +181 -60
  12. {euroeval-16.2.1 → euroeval-16.3.0}/README.md +178 -57
  13. {euroeval-16.2.1 → euroeval-16.3.0}/docs/README.md +9 -4
  14. {euroeval-16.2.1 → euroeval-16.3.0}/docs/datasets/README.md +1 -1
  15. {euroeval-16.2.1 → euroeval-16.3.0}/docs/datasets/danish.md +169 -83
  16. {euroeval-16.2.1 → euroeval-16.3.0}/docs/datasets/dutch.md +145 -72
  17. {euroeval-16.2.1 → euroeval-16.3.0}/docs/datasets/english.md +157 -77
  18. {euroeval-16.2.1 → euroeval-16.3.0}/docs/datasets/estonian.md +113 -59
  19. {euroeval-16.2.1 → euroeval-16.3.0}/docs/datasets/faroese.md +94 -54
  20. {euroeval-16.2.1 → euroeval-16.3.0}/docs/datasets/finnish.md +121 -60
  21. {euroeval-16.2.1 → euroeval-16.3.0}/docs/datasets/french.md +128 -64
  22. {euroeval-16.2.1 → euroeval-16.3.0}/docs/datasets/german.md +165 -79
  23. {euroeval-16.2.1 → euroeval-16.3.0}/docs/datasets/icelandic.md +187 -92
  24. {euroeval-16.2.1 → euroeval-16.3.0}/docs/datasets/italian.md +149 -75
  25. {euroeval-16.2.1 → euroeval-16.3.0}/docs/datasets/latvian.md +122 -65
  26. euroeval-16.3.0/docs/datasets/lithuanian.md +452 -0
  27. {euroeval-16.2.1 → euroeval-16.3.0}/docs/datasets/norwegian.md +286 -141
  28. {euroeval-16.2.1 → euroeval-16.3.0}/docs/datasets/polish.md +113 -56
  29. {euroeval-16.2.1 → euroeval-16.3.0}/docs/datasets/portuguese.md +165 -75
  30. {euroeval-16.2.1 → euroeval-16.3.0}/docs/datasets/spanish.md +152 -66
  31. {euroeval-16.2.1 → euroeval-16.3.0}/docs/datasets/swedish.md +185 -84
  32. {euroeval-16.2.1 → euroeval-16.3.0}/docs/extras/radial_plotter.md +2 -2
  33. {euroeval-16.2.1 → euroeval-16.3.0}/docs/leaderboards/Monolingual/danish.md +2 -0
  34. {euroeval-16.2.1 → euroeval-16.3.0}/docs/leaderboards/Monolingual/dutch.md +2 -0
  35. {euroeval-16.2.1 → euroeval-16.3.0}/docs/leaderboards/Monolingual/english.md +2 -0
  36. {euroeval-16.2.1 → euroeval-16.3.0}/docs/leaderboards/Monolingual/estonian.md +4 -2
  37. {euroeval-16.2.1 → euroeval-16.3.0}/docs/leaderboards/Monolingual/faroese.md +2 -0
  38. {euroeval-16.2.1 → euroeval-16.3.0}/docs/leaderboards/Monolingual/finnish.md +2 -0
  39. {euroeval-16.2.1 → euroeval-16.3.0}/docs/leaderboards/Monolingual/french.md +2 -0
  40. {euroeval-16.2.1 → euroeval-16.3.0}/docs/leaderboards/Monolingual/german.md +2 -0
  41. {euroeval-16.2.1 → euroeval-16.3.0}/docs/leaderboards/Monolingual/icelandic.md +2 -0
  42. {euroeval-16.2.1 → euroeval-16.3.0}/docs/leaderboards/Monolingual/italian.md +2 -0
  43. euroeval-16.3.0/docs/leaderboards/Monolingual/latvian.md +25 -0
  44. {euroeval-16.2.1 → euroeval-16.3.0}/docs/leaderboards/Monolingual/norwegian.md +2 -0
  45. {euroeval-16.2.1 → euroeval-16.3.0}/docs/leaderboards/Monolingual/portuguese.md +2 -0
  46. {euroeval-16.2.1 → euroeval-16.3.0}/docs/leaderboards/Monolingual/spanish.md +2 -0
  47. {euroeval-16.2.1 → euroeval-16.3.0}/docs/leaderboards/Monolingual/swedish.md +2 -0
  48. {euroeval-16.2.1 → euroeval-16.3.0}/docs/leaderboards/Multilingual/european.md +2 -0
  49. {euroeval-16.2.1 → euroeval-16.3.0}/docs/leaderboards/Multilingual/finnic.md +4 -2
  50. {euroeval-16.2.1 → euroeval-16.3.0}/docs/leaderboards/Multilingual/germanic.md +2 -0
  51. {euroeval-16.2.1 → euroeval-16.3.0}/docs/leaderboards/Multilingual/mainland-scandinavian.md +2 -0
  52. {euroeval-16.2.1 → euroeval-16.3.0}/docs/leaderboards/Multilingual/romance.md +2 -0
  53. {euroeval-16.2.1 → euroeval-16.3.0}/docs/leaderboards/README.md +4 -6
  54. {euroeval-16.2.1 → euroeval-16.3.0}/docs/methodology.md +2 -5
  55. {euroeval-16.2.1 → euroeval-16.3.0}/docs/python-package.md +10 -12
  56. {euroeval-16.2.1 → euroeval-16.3.0}/docs/tasks/README.md +0 -2
  57. {euroeval-16.2.1 → euroeval-16.3.0}/docs/tasks/common-sense-reasoning.md +1 -3
  58. {euroeval-16.2.1 → euroeval-16.3.0}/docs/tasks/knowledge.md +1 -3
  59. {euroeval-16.2.1 → euroeval-16.3.0}/docs/tasks/linguistic-acceptability.md +1 -3
  60. {euroeval-16.2.1 → euroeval-16.3.0}/docs/tasks/named-entity-recognition.md +1 -3
  61. {euroeval-16.2.1 → euroeval-16.3.0}/docs/tasks/reading-comprehension.md +1 -3
  62. {euroeval-16.2.1 → euroeval-16.3.0}/docs/tasks/sentiment-classification.md +1 -3
  63. {euroeval-16.2.1 → euroeval-16.3.0}/docs/tasks/speed.md +1 -3
  64. {euroeval-16.2.1 → euroeval-16.3.0}/docs/tasks/summarization.md +1 -3
  65. {euroeval-16.2.1 → euroeval-16.3.0}/makefile +1 -1
  66. {euroeval-16.2.1 → euroeval-16.3.0}/pyproject.toml +5 -5
  67. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/__init__.py +4 -2
  68. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/benchmark_modules/fresh.py +3 -1
  69. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/benchmark_modules/hf.py +8 -4
  70. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/benchmark_modules/litellm.py +5 -17
  71. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/benchmark_modules/vllm.py +98 -30
  72. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/benchmarker.py +291 -405
  73. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/cli.py +1 -1
  74. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/constants.py +3 -0
  75. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/dataset_configs/__init__.py +1 -0
  76. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/dataset_configs/danish.py +0 -2
  77. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/dataset_configs/dutch.py +0 -2
  78. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/dataset_configs/english.py +0 -2
  79. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/dataset_configs/finnish.py +0 -2
  80. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/dataset_configs/french.py +0 -2
  81. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/dataset_configs/german.py +0 -2
  82. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/dataset_configs/italian.py +0 -2
  83. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/dataset_configs/latvian.py +2 -3
  84. euroeval-16.3.0/src/euroeval/dataset_configs/lithuanian.py +62 -0
  85. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/dataset_configs/norwegian.py +0 -2
  86. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/dataset_configs/polish.py +0 -2
  87. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/dataset_configs/portuguese.py +0 -2
  88. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/dataset_configs/spanish.py +0 -2
  89. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/dataset_configs/swedish.py +0 -3
  90. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/metrics/huggingface.py +1 -1
  91. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/metrics/pipeline.py +5 -0
  92. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/prompt_templates/linguistic_acceptability.py +9 -0
  93. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/prompt_templates/multiple_choice.py +9 -0
  94. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/prompt_templates/named_entity_recognition.py +20 -0
  95. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/prompt_templates/reading_comprehension.py +10 -0
  96. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/prompt_templates/sentiment_classification.py +11 -0
  97. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/tokenisation_utils.py +8 -8
  98. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/utils.py +10 -5
  99. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/constants.py +1 -0
  100. euroeval-16.3.0/src/scripts/create_lt_emotions.py +159 -0
  101. euroeval-16.3.0/src/scripts/create_lt_history.py +147 -0
  102. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_multi_wiki_qa.py +1 -0
  103. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_scala.py +2 -0
  104. euroeval-16.3.0/src/scripts/create_wikiann.py +115 -0
  105. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_winogrande.py +1 -0
  106. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/load_ud_pos.py +18 -0
  107. {euroeval-16.2.1 → euroeval-16.3.0}/tests/conftest.py +23 -1
  108. {euroeval-16.2.1 → euroeval-16.3.0}/tests/test_benchmarker.py +39 -51
  109. euroeval-16.3.0/tests/test_cli.py +69 -0
  110. {euroeval-16.2.1 → euroeval-16.3.0}/tests/test_data_models.py +47 -9
  111. {euroeval-16.2.1 → euroeval-16.3.0}/uv.lock +3 -3
  112. euroeval-16.2.1/src/scripts/create_wikiann_lv.py +0 -107
  113. euroeval-16.2.1/tests/test_cli.py +0 -81
  114. {euroeval-16.2.1 → euroeval-16.3.0}/.github/ISSUE_TEMPLATE/language_request.yaml +0 -0
  115. {euroeval-16.2.1 → euroeval-16.3.0}/.github/workflows/ci.yaml +0 -0
  116. {euroeval-16.2.1 → euroeval-16.3.0}/.gitignore +0 -0
  117. {euroeval-16.2.1 → euroeval-16.3.0}/CITATION.cff +0 -0
  118. {euroeval-16.2.1 → euroeval-16.3.0}/Dockerfile.cuda +0 -0
  119. {euroeval-16.2.1 → euroeval-16.3.0}/LICENSE +0 -0
  120. {euroeval-16.2.1 → euroeval-16.3.0}/docs/CNAME +0 -0
  121. {euroeval-16.2.1 → euroeval-16.3.0}/docs/faq.md +0 -0
  122. {euroeval-16.2.1 → euroeval-16.3.0}/docs/gfx/favicon.png +0 -0
  123. {euroeval-16.2.1 → euroeval-16.3.0}/gfx/euroeval.png +0 -0
  124. {euroeval-16.2.1 → euroeval-16.3.0}/gfx/euroeval.xcf +0 -0
  125. {euroeval-16.2.1 → euroeval-16.3.0}/gfx/scandeval.png +0 -0
  126. {euroeval-16.2.1 → euroeval-16.3.0}/mkdocs.yaml +0 -0
  127. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/benchmark_config_factory.py +0 -0
  128. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/benchmark_modules/__init__.py +0 -0
  129. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/benchmark_modules/base.py +0 -0
  130. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/callbacks.py +0 -0
  131. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/data_loading.py +0 -0
  132. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/data_models.py +35 -35
  133. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/dataset_configs/estonian.py +0 -0
  134. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/dataset_configs/faroese.py +0 -0
  135. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/dataset_configs/icelandic.py +0 -0
  136. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/enums.py +0 -0
  137. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/exceptions.py +0 -0
  138. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/finetuning.py +0 -0
  139. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/generation.py +0 -0
  140. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/generation_utils.py +0 -0
  141. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/languages.py +0 -0
  142. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/metrics/__init__.py +0 -0
  143. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/metrics/base.py +0 -0
  144. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/metrics/llm_as_a_judge.py +0 -0
  145. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/metrics/speed.py +0 -0
  146. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/model_cache.py +0 -0
  147. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/model_config.py +0 -0
  148. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/model_loading.py +0 -0
  149. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/prompt_templates/__init__.py +0 -0
  150. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/prompt_templates/summarization.py +0 -0
  151. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/scores.py +0 -0
  152. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/speed_benchmark.py +0 -0
  153. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/task_group_utils/__init__.py +0 -0
  154. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/task_group_utils/multiple_choice_classification.py +0 -0
  155. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/task_group_utils/question_answering.py +0 -0
  156. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/task_group_utils/sequence_classification.py +0 -0
  157. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/task_group_utils/text_to_text.py +0 -0
  158. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/task_group_utils/token_classification.py +0 -0
  159. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/tasks.py +0 -0
  160. {euroeval-16.2.1 → euroeval-16.3.0}/src/euroeval/types.py +0 -0
  161. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_allocine.py +0 -0
  162. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_angry_tweets.py +0 -0
  163. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_arc.py +0 -0
  164. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_arc_is.py +0 -0
  165. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_belebele.py +0 -0
  166. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_boolq_pt.py +0 -0
  167. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_cnn_dailymail.py +0 -0
  168. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_conll_en.py +0 -0
  169. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_conll_es.py +0 -0
  170. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_conll_nl.py +0 -0
  171. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_copa_lv.py +0 -0
  172. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_dane.py +0 -0
  173. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_danish_citizen_tests.py +0 -0
  174. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_dansk.py +0 -0
  175. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_danske_talemaader.py +0 -0
  176. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_danske_talemaader_old.py +0 -0
  177. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_dbrd.py +0 -0
  178. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_dutch_cola.py +0 -0
  179. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_eltec.py +0 -0
  180. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_err_news.py +0 -0
  181. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_estner.py +0 -0
  182. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_estonian_valence.py +0 -0
  183. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_european_values.py +0 -0
  184. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_exam_et.py +0 -0
  185. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_fone.py +0 -0
  186. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_foqa.py +0 -0
  187. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_fosent.py +0 -0
  188. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_fquad.py +0 -0
  189. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_fullstack_ner.py +0 -0
  190. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_germanquad.py +0 -0
  191. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_germeval.py +0 -0
  192. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_goldenswag.py +0 -0
  193. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_grammar_et.py +0 -0
  194. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_harem.py +0 -0
  195. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_hellaswag.py +0 -0
  196. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_hellaswag_fi.py +0 -0
  197. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_hotter_and_colder_sentiment.py +0 -0
  198. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_ice_linguistic.py +0 -0
  199. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_icelandic_error_corpus.py +0 -0
  200. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_icelandic_knowledge.py +0 -0
  201. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_icelandic_qa.py +0 -0
  202. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_icesum.py +0 -0
  203. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_idioms_no.py +0 -0
  204. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_ilpost_sum.py +0 -0
  205. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_jentoft.py +0 -0
  206. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_kpwr_ner.py +0 -0
  207. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_latvian_lsm_summary.py +0 -0
  208. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_latvian_twitter_sentiment.py +0 -0
  209. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_life_in_the_uk.py +0 -0
  210. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_llmzszl.py +0 -0
  211. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_mim_gold_ner.py +0 -0
  212. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_mlqa_es.py +0 -0
  213. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_mlsum_de.py +0 -0
  214. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_mlsum_es.py +0 -0
  215. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_mmlu.py +0 -0
  216. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_mmlu_lv.py +0 -0
  217. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_multinerd-it.py +0 -0
  218. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_no_cola.py +0 -0
  219. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_no_sammendrag.py +0 -0
  220. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_nor_common_sense_qa.py +0 -0
  221. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_nordjylland_news.py +0 -0
  222. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_norec.py +0 -0
  223. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_norglm_multiqa.py +0 -0
  224. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_norglm_multisum.py +0 -0
  225. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_norne.py +0 -0
  226. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_norquad.py +0 -0
  227. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_nqii.py +0 -0
  228. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_nrk_quiz_qa.py +0 -0
  229. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_orange_sum.py +0 -0
  230. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_personal_sum.py +0 -0
  231. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_polemo2.py +0 -0
  232. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_poquad.py +0 -0
  233. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_psc.py +0 -0
  234. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_publico.py +0 -0
  235. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_rrn.py +0 -0
  236. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_sb10k.py +0 -0
  237. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_scandiqa.py +0 -0
  238. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_scandisent_fi.py +0 -0
  239. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_schibsted.py +0 -0
  240. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_sentiment_headlines_es.py +0 -0
  241. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_sentipolc16.py +0 -0
  242. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_squad.py +0 -0
  243. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_squad_it.py +0 -0
  244. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_squad_nl.py +0 -0
  245. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_squad_nl_old.py +0 -0
  246. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_sst2_pt.py +0 -0
  247. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_sst5.py +0 -0
  248. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_suc3.py +0 -0
  249. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_swedish_skolprov.py +0 -0
  250. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_swedn.py +0 -0
  251. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_swerec.py +0 -0
  252. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_trivia_et.py +0 -0
  253. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_turku_ner_fi.py +0 -0
  254. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_tydiqa_fi.py +0 -0
  255. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_wiki_lingua_nl.py +0 -0
  256. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_wikineural-it.py +0 -0
  257. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_winogrande_et.py +0 -0
  258. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_winogrande_is.py +0 -0
  259. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_xlsum_fi.py +0 -0
  260. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/create_xquad.py +0 -0
  261. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/fix_dot_env_file.py +0 -0
  262. {euroeval-16.2.1 → euroeval-16.3.0}/src/scripts/versioning.py +0 -0
  263. {euroeval-16.2.1 → euroeval-16.3.0}/tests/__init__.py +0 -0
  264. {euroeval-16.2.1 → euroeval-16.3.0}/tests/test_benchmark_config_factory.py +0 -0
  265. {euroeval-16.2.1 → euroeval-16.3.0}/tests/test_benchmark_modules/__init__.py +0 -0
  266. {euroeval-16.2.1 → euroeval-16.3.0}/tests/test_benchmark_modules/test_hf.py +0 -0
  267. {euroeval-16.2.1 → euroeval-16.3.0}/tests/test_callbacks.py +0 -0
  268. {euroeval-16.2.1 → euroeval-16.3.0}/tests/test_constants.py +0 -0
  269. {euroeval-16.2.1 → euroeval-16.3.0}/tests/test_data_loading.py +0 -0
  270. {euroeval-16.2.1 → euroeval-16.3.0}/tests/test_dataset_configs.py +0 -0
  271. {euroeval-16.2.1 → euroeval-16.3.0}/tests/test_enums.py +0 -0
  272. {euroeval-16.2.1 → euroeval-16.3.0}/tests/test_exceptions.py +0 -0
  273. {euroeval-16.2.1 → euroeval-16.3.0}/tests/test_finetuning.py +0 -0
  274. {euroeval-16.2.1 → euroeval-16.3.0}/tests/test_languages.py +0 -0
  275. {euroeval-16.2.1 → euroeval-16.3.0}/tests/test_model_config.py +0 -0
  276. {euroeval-16.2.1 → euroeval-16.3.0}/tests/test_model_loading.py +0 -0
  277. {euroeval-16.2.1 → euroeval-16.3.0}/tests/test_scores.py +0 -0
  278. {euroeval-16.2.1 → euroeval-16.3.0}/tests/test_speed_benchmark.py +0 -0
  279. {euroeval-16.2.1 → euroeval-16.3.0}/tests/test_tasks.py +0 -0
  280. {euroeval-16.2.1 → euroeval-16.3.0}/tests/test_tokenisation_utils.py +0 -0
  281. {euroeval-16.2.1 → euroeval-16.3.0}/tests/test_types.py +0 -0
  282. {euroeval-16.2.1 → euroeval-16.3.0}/tests/test_utils.py +0 -0
@@ -14,7 +14,9 @@ body:
14
14
  - type: input
15
15
  attributes:
16
16
  label: Dataset link
17
- description: Please give a link to where the dataset is hosted (doesn't have to be on the Hugging Face Hub)
17
+ description: >
18
+ Please give a link to where the dataset is hosted (doesn't have to be on the
19
+ Hugging Face Hub)
18
20
  validations:
19
21
  required: true
20
22
  - type: checkboxes
@@ -33,6 +35,7 @@ body:
33
35
  - label: Icelandic
34
36
  - label: Italian
35
37
  - label: Latvian
38
+ - label: Lithuanian
36
39
  - label: Norwegian (Bokmål or Nynorsk)
37
40
  - label: Polish
38
41
  - label: Portuguese
@@ -43,7 +46,9 @@ body:
43
46
  - type: textarea
44
47
  attributes:
45
48
  label: Describe the dataset
46
- description: Describe what the dataset is measuring, and why you think it is important to include it as a benchmark dataset in EuroEval.
49
+ description: >
50
+ Describe what the dataset is measuring, and why you think it is important to
51
+ include it as a benchmark dataset in EuroEval.
47
52
  validations:
48
53
  required: true
49
54
  - type: markdown
@@ -7,12 +7,15 @@ body:
7
7
  - type: markdown
8
8
  attributes:
9
9
  value: >
10
- #### Before submitting a bug, please make sure the issue hasn't been already addressed by searching through [the existing and past issues](https://github.com/EuroEval/EuroEval/issues?q=is%3Aissue).
10
+ Before submitting a bug, please make sure the issue hasn't been already addressed
11
+ by searching through [the existing and past
12
+ issues](https://github.com/EuroEval/EuroEval/issues?q=is%3Aissue).
11
13
  - type: textarea
12
14
  attributes:
13
15
  label: 🐛 Describe the bug
14
- description: |
15
- Please provide a clear and concise description of what the bug is. If relevant, add a minimal example so that we can reproduce the error by running the code.
16
+ description: >
17
+ Please provide a clear and concise description of what the bug is. If relevant,
18
+ add a minimal example so that we can reproduce the error by running the code.
16
19
  validations:
17
20
  required: true
18
21
  - type: dropdown
@@ -8,7 +8,9 @@ body:
8
8
  attributes:
9
9
  label: 🚀 The feature, motivation and pitch
10
10
  description: >
11
- A clear and concise description of the feature proposal. Please outline the motivation for the proposal. Is your feature request related to a specific problem? e.g., *"I'm working on X and would like Y to be possible"*.
11
+ A clear and concise description of the feature proposal. Please outline the
12
+ motivation for the proposal. Is your feature request related to a specific
13
+ problem? e.g., *"I'm working on X and would like Y to be possible"*.
12
14
  validations:
13
15
  required: true
14
16
  - type: markdown
@@ -22,7 +22,7 @@ body:
22
22
  - label: Scandinavian languages (Danish, Faroese, Icelandic, Norwegian, Swedish)
23
23
  - label: West Germanic languages (Dutch, English, German)
24
24
  - label: Finnic languages (Estonian, Finnish)
25
- - label: Latvian
25
+ - label: Baltic languages (Latvian, Lithuanian)
26
26
  - label: Polish
27
27
  validations:
28
28
  required: true
@@ -49,7 +49,8 @@ body:
49
49
  - type: dropdown
50
50
  attributes:
51
51
  label: Merged model
52
- description: Is the model a merge of other models, or built on top of a merged model?
52
+ description: >
53
+ Is the model a merge of other models, or built on top of a merged model?
53
54
  options:
54
55
  - Not a merged model
55
56
  - Merged model
@@ -0,0 +1,10 @@
1
+ {
2
+ "MD013": {
3
+ "line_length": 88,
4
+ "code_blocks": false,
5
+ "tables": false
6
+ }, // Set maximum line length to 88 characters, except in code blocks and tables
7
+ "MD024": false, // Allow duplicate headings
8
+ "MD033": false, // Allow inline HTML
9
+ "MD059": false // Allow non-descriptive link text
10
+ }
@@ -10,7 +10,7 @@ repos:
10
10
  - id: trailing-whitespace
11
11
  - id: debug-statements
12
12
  - repo: https://github.com/astral-sh/ruff-pre-commit
13
- rev: v0.13.0
13
+ rev: v0.13.1
14
14
  hooks:
15
15
  - id: ruff
16
16
  args:
@@ -34,7 +34,7 @@ repos:
34
34
  hooks:
35
35
  - id: nbstripout
36
36
  - repo: https://github.com/pre-commit/mirrors-mypy
37
- rev: v1.18.1
37
+ rev: v1.18.2
38
38
  hooks:
39
39
  - id: mypy
40
40
  args:
@@ -43,3 +43,9 @@ repos:
43
43
  - --ignore-missing-imports
44
44
  - --show-error-codes
45
45
  - --check-untyped-defs
46
+ - repo: https://github.com/DavidAnson/markdownlint-cli2
47
+ rev: v0.18.1
48
+ hooks:
49
+ - id: markdownlint-cli2
50
+ args:
51
+ - --fix