evalscope 0.7.0__tar.gz → 0.7.1__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 evalscope might be problematic. Click here for more details.

Files changed (304) hide show
  1. {evalscope-0.7.0/evalscope.egg-info → evalscope-0.7.1}/PKG-INFO +3 -3
  2. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/opencompass/tasks/eval_api.py +2 -1
  3. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/opencompass/tasks/eval_datasets.py +1 -0
  4. evalscope-0.7.1/evalscope/version.py +4 -0
  5. {evalscope-0.7.0 → evalscope-0.7.1/evalscope.egg-info}/PKG-INFO +3 -3
  6. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope.egg-info/requires.txt +2 -2
  7. evalscope-0.7.1/requirements/opencompass.txt +1 -0
  8. evalscope-0.7.0/evalscope/version.py +0 -4
  9. evalscope-0.7.0/requirements/opencompass.txt +0 -1
  10. {evalscope-0.7.0 → evalscope-0.7.1}/LICENSE +0 -0
  11. {evalscope-0.7.0 → evalscope-0.7.1}/MANIFEST.in +0 -0
  12. {evalscope-0.7.0 → evalscope-0.7.1}/README.md +0 -0
  13. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/__init__.py +0 -0
  14. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/__init__.py +0 -0
  15. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/base.py +0 -0
  16. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/opencompass/__init__.py +0 -0
  17. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/opencompass/api_meta_template.py +0 -0
  18. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/opencompass/backend_manager.py +0 -0
  19. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/opencompass/tasks/__init__.py +0 -0
  20. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/__init__.py +0 -0
  21. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/backend_manager.py +0 -0
  22. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/clip_benchmark/__init__.py +0 -0
  23. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/clip_benchmark/arguments.py +0 -0
  24. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/clip_benchmark/dataset_builder.py +0 -0
  25. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/clip_benchmark/task_template.py +0 -0
  26. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/clip_benchmark/tasks/__init__.py +0 -0
  27. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/clip_benchmark/tasks/image_caption.py +0 -0
  28. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/clip_benchmark/tasks/zeroshot_classification.py +0 -0
  29. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/clip_benchmark/tasks/zeroshot_retrieval.py +0 -0
  30. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/clip_benchmark/utils/webdataset_convert.py +0 -0
  31. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/clip_benchmark/utils/webdatasets.txt +0 -0
  32. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/cmteb/__init__.py +0 -0
  33. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/cmteb/arguments.py +0 -0
  34. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/cmteb/base.py +0 -0
  35. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/cmteb/task_template.py +0 -0
  36. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/cmteb/tasks/Classification.py +0 -0
  37. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/cmteb/tasks/Clustering.py +0 -0
  38. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/cmteb/tasks/CustomTask.py +0 -0
  39. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/cmteb/tasks/PairClassification.py +0 -0
  40. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/cmteb/tasks/Reranking.py +0 -0
  41. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/cmteb/tasks/Retrieval.py +0 -0
  42. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/cmteb/tasks/STS.py +0 -0
  43. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/cmteb/tasks/__init__.py +0 -0
  44. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/__init__.py +0 -0
  45. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/arguments.py +0 -0
  46. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/metrics/__init__.py +0 -0
  47. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/metrics/multi_modal_faithfulness.py +0 -0
  48. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/metrics/multi_modal_relevance.py +0 -0
  49. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/prompts/chinese/AnswerCorrectness/correctness_prompt_chinese.json +0 -0
  50. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/prompts/chinese/AnswerCorrectness/long_form_answer_prompt_chinese.json +0 -0
  51. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/prompts/chinese/AnswerRelevancy/question_generation_chinese.json +0 -0
  52. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/prompts/chinese/ContextPrecision/context_precision_prompt_chinese.json +0 -0
  53. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/prompts/chinese/Faithfulness/nli_statements_message_chinese.json +0 -0
  54. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/prompts/chinese/Faithfulness/statement_prompt_chinese.json +0 -0
  55. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/prompts/chinese/HeadlinesExtractor/prompt_chinese.json +0 -0
  56. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/prompts/chinese/MultiHopAbstractQuerySynthesizer/concept_combination_prompt_chinese.json +0 -0
  57. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/prompts/chinese/MultiHopAbstractQuerySynthesizer/generate_query_reference_prompt_chinese.json +0 -0
  58. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/prompts/chinese/MultiHopAbstractQuerySynthesizer/theme_persona_matching_prompt_chinese.json +0 -0
  59. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/prompts/chinese/MultiHopSpecificQuerySynthesizer/generate_query_reference_prompt_chinese.json +0 -0
  60. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/prompts/chinese/MultiHopSpecificQuerySynthesizer/theme_persona_matching_prompt_chinese.json +0 -0
  61. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/prompts/chinese/MultiModalFaithfulness/faithfulness_prompt_chinese.json +0 -0
  62. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/prompts/chinese/MultiModalRelevance/relevance_prompt_chinese.json +0 -0
  63. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/prompts/chinese/NERExtractor/prompt_chinese.json +0 -0
  64. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/prompts/chinese/SingleHopSpecificQuerySynthesizer/generate_query_reference_prompt_chinese.json +0 -0
  65. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/prompts/chinese/SingleHopSpecificQuerySynthesizer/theme_persona_matching_prompt_chinese.json +0 -0
  66. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/prompts/chinese/SummaryExtractor/prompt_chinese.json +0 -0
  67. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/prompts/chinese/ThemesExtractor/prompt_chinese.json +0 -0
  68. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/prompts/persona_prompt.py +0 -0
  69. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/task_template.py +0 -0
  70. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/tasks/__init__.py +0 -0
  71. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/tasks/testset_generation.py +0 -0
  72. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/ragas/tasks/translate_prompt.py +0 -0
  73. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/utils/__init__.py +0 -0
  74. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/utils/clip.py +0 -0
  75. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/utils/embedding.py +0 -0
  76. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/utils/llm.py +0 -0
  77. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/rag_eval/utils/tools.py +0 -0
  78. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/vlm_eval_kit/__init__.py +0 -0
  79. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/vlm_eval_kit/backend_manager.py +0 -0
  80. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/vlm_eval_kit/custom_dataset.py +0 -0
  81. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/__init__.py +0 -0
  82. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/arc/__init__.py +0 -0
  83. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/arc/ai2_arc.py +0 -0
  84. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/arc/arc_adapter.py +0 -0
  85. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/__init__.py +0 -0
  86. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/bbh_adapter.py +0 -0
  87. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/boolean_expressions.txt +0 -0
  88. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/causal_judgement.txt +0 -0
  89. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/date_understanding.txt +0 -0
  90. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/disambiguation_qa.txt +0 -0
  91. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/dyck_languages.txt +0 -0
  92. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/formal_fallacies.txt +0 -0
  93. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/geometric_shapes.txt +0 -0
  94. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/hyperbaton.txt +0 -0
  95. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/logical_deduction_five_objects.txt +0 -0
  96. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/logical_deduction_seven_objects.txt +0 -0
  97. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/logical_deduction_three_objects.txt +0 -0
  98. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/movie_recommendation.txt +0 -0
  99. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/multistep_arithmetic_two.txt +0 -0
  100. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/navigate.txt +0 -0
  101. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/object_counting.txt +0 -0
  102. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/penguins_in_a_table.txt +0 -0
  103. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/reasoning_about_colored_objects.txt +0 -0
  104. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/ruin_names.txt +0 -0
  105. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/salient_translation_error_detection.txt +0 -0
  106. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/snarks.txt +0 -0
  107. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/sports_understanding.txt +0 -0
  108. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/temporal_sequences.txt +0 -0
  109. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/tracking_shuffled_objects_five_objects.txt +0 -0
  110. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/tracking_shuffled_objects_seven_objects.txt +0 -0
  111. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/tracking_shuffled_objects_three_objects.txt +0 -0
  112. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/web_of_lies.txt +0 -0
  113. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/bbh/cot_prompts/word_sorting.txt +0 -0
  114. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/benchmark.py +0 -0
  115. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/ceval/__init__.py +0 -0
  116. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/ceval/ceval_adapter.py +0 -0
  117. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/ceval/ceval_exam.py +0 -0
  118. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/ceval/samples.jsonl +0 -0
  119. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/cmmlu/__init__.py +0 -0
  120. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/cmmlu/cmmlu.py +0 -0
  121. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/cmmlu/cmmlu_adapter.py +0 -0
  122. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/cmmlu/samples.jsonl +0 -0
  123. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/competition_math/__init__.py +0 -0
  124. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/competition_math/competition_math.py +0 -0
  125. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/competition_math/competition_math_adapter.py +0 -0
  126. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/data_adapter.py +0 -0
  127. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/general_qa/__init__.py +0 -0
  128. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/general_qa/general_qa_adapter.py +0 -0
  129. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/gsm8k/__init__.py +0 -0
  130. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/gsm8k/gsm8k.py +0 -0
  131. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/gsm8k/gsm8k_adapter.py +0 -0
  132. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/hellaswag/__init__.py +0 -0
  133. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/hellaswag/hellaswag.py +0 -0
  134. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/hellaswag/hellaswag_adapter.py +0 -0
  135. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/humaneval/__init__.py +0 -0
  136. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/humaneval/humaneval.py +0 -0
  137. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/humaneval/humaneval_adapter.py +0 -0
  138. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/mmlu/__init__.py +0 -0
  139. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/mmlu/mmlu.py +0 -0
  140. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/mmlu/mmlu_adapter.py +0 -0
  141. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/mmlu/samples.jsonl +0 -0
  142. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/race/__init__.py +0 -0
  143. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/race/race.py +0 -0
  144. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/race/race_adapter.py +0 -0
  145. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/race/samples.jsonl +0 -0
  146. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/trivia_qa/__init__.py +0 -0
  147. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/trivia_qa/samples.jsonl +0 -0
  148. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/trivia_qa/trivia_qa.py +0 -0
  149. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/trivia_qa/trivia_qa_adapter.py +0 -0
  150. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/truthful_qa/__init__.py +0 -0
  151. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/truthful_qa/truthful_qa.py +0 -0
  152. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/benchmarks/truthful_qa/truthful_qa_adapter.py +0 -0
  153. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/cache.py +0 -0
  154. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/cli/__init__.py +0 -0
  155. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/cli/base.py +0 -0
  156. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/cli/cli.py +0 -0
  157. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/cli/start_perf.py +0 -0
  158. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/cli/start_server.py +0 -0
  159. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/config.py +0 -0
  160. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/constants.py +0 -0
  161. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/evaluator/__init__.py +0 -0
  162. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/evaluator/evaluator.py +0 -0
  163. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/evaluator/rating_eval.py +0 -0
  164. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/evaluator/reviewer/__init__.py +0 -0
  165. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/evaluator/reviewer/auto_reviewer.py +0 -0
  166. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/metrics/__init__.py +0 -0
  167. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/metrics/bundled_rouge_score/__init__.py +0 -0
  168. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/metrics/bundled_rouge_score/rouge_scorer.py +0 -0
  169. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/metrics/code_metric.py +0 -0
  170. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/metrics/math_accuracy.py +0 -0
  171. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/metrics/metrics.py +0 -0
  172. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/metrics/resources/gpt2-zhcn3-v4.bpe +0 -0
  173. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/metrics/resources/gpt2-zhcn3-v4.json +0 -0
  174. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/metrics/rouge_metric.py +0 -0
  175. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/models/__init__.py +0 -0
  176. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/models/api/__init__.py +0 -0
  177. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/models/api/openai_api.py +0 -0
  178. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/models/custom/__init__.py +0 -0
  179. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/models/custom/custom_model.py +0 -0
  180. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/models/dummy_chat_model.py +0 -0
  181. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/models/model.py +0 -0
  182. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/models/model_adapter.py +0 -0
  183. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/models/openai_model.py +0 -0
  184. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/models/template.py +0 -0
  185. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/__init__.py +0 -0
  186. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/arguments.py +0 -0
  187. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/benchmark.py +0 -0
  188. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/http_client.py +0 -0
  189. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/main.py +0 -0
  190. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/plugin/__init__.py +0 -0
  191. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/plugin/api/__init__.py +0 -0
  192. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/plugin/api/base.py +0 -0
  193. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/plugin/api/custom_api.py +0 -0
  194. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/plugin/api/dashscope_api.py +0 -0
  195. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/plugin/api/openai_api.py +0 -0
  196. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/plugin/datasets/__init__.py +0 -0
  197. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/plugin/datasets/base.py +0 -0
  198. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/plugin/datasets/custom.py +0 -0
  199. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/plugin/datasets/flickr8k.py +0 -0
  200. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/plugin/datasets/line_by_line.py +0 -0
  201. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/plugin/datasets/longalpaca.py +0 -0
  202. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/plugin/datasets/openqa.py +0 -0
  203. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/plugin/datasets/speed_benchmark.py +0 -0
  204. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/plugin/registry.py +0 -0
  205. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/utils/__init__.py +0 -0
  206. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/utils/analysis_result.py +0 -0
  207. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/utils/benchmark_util.py +0 -0
  208. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/utils/chat_service.py +0 -0
  209. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/utils/db_util.py +0 -0
  210. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/utils/handler.py +0 -0
  211. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/perf/utils/local_server.py +0 -0
  212. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/registry/__init__.py +0 -0
  213. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/registry/config/cfg_arena.yaml +0 -0
  214. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/registry/config/cfg_arena_zhihu.yaml +0 -0
  215. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/registry/config/cfg_pairwise_baseline.yaml +0 -0
  216. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/registry/config/cfg_single.yaml +0 -0
  217. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/registry/data/prompt_template/lmsys_v2.jsonl +0 -0
  218. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/registry/data/prompt_template/prompt_templates.jsonl +0 -0
  219. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/registry/data/qa_browser/battle.jsonl +0 -0
  220. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/registry/data/qa_browser/category_mapping.yaml +0 -0
  221. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/registry/data/question.jsonl +0 -0
  222. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/registry/tasks/arc.yaml +0 -0
  223. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/registry/tasks/bbh.yaml +0 -0
  224. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/registry/tasks/bbh_mini.yaml +0 -0
  225. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/registry/tasks/ceval.yaml +0 -0
  226. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/registry/tasks/ceval_mini.yaml +0 -0
  227. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/registry/tasks/cmmlu.yaml +0 -0
  228. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/registry/tasks/eval_qwen-7b-chat_v100.yaml +0 -0
  229. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/registry/tasks/general_qa.yaml +0 -0
  230. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/registry/tasks/gsm8k.yaml +0 -0
  231. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/registry/tasks/mmlu.yaml +0 -0
  232. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/registry/tasks/mmlu_mini.yaml +0 -0
  233. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/run.py +0 -0
  234. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/run_arena.py +0 -0
  235. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/run_ms.py +0 -0
  236. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/summarizer.py +0 -0
  237. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/__init__.py +0 -0
  238. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/longbench_write/README.md +0 -0
  239. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/longbench_write/__init__.py +0 -0
  240. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/longbench_write/default_task.json +0 -0
  241. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/longbench_write/default_task.yaml +0 -0
  242. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/longbench_write/eval.py +0 -0
  243. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/longbench_write/infer.py +0 -0
  244. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/longbench_write/longbench_write.py +0 -0
  245. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/longbench_write/resources/__init__.py +0 -0
  246. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/longbench_write/resources/judge.txt +0 -0
  247. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/longbench_write/resources/longbench_write.jsonl +0 -0
  248. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/longbench_write/resources/longbench_write_en.jsonl +0 -0
  249. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/longbench_write/resources/longwrite_ruler.jsonl +0 -0
  250. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/longbench_write/tools/__init__.py +0 -0
  251. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/longbench_write/tools/data_etl.py +0 -0
  252. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/longbench_write/utils.py +0 -0
  253. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/toolbench_static/README.md +0 -0
  254. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/toolbench_static/__init__.py +0 -0
  255. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/toolbench_static/config_default.json +0 -0
  256. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/toolbench_static/config_default.yaml +0 -0
  257. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/toolbench_static/eval.py +0 -0
  258. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/toolbench_static/infer.py +0 -0
  259. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/toolbench_static/llm/__init__.py +0 -0
  260. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/toolbench_static/llm/swift_infer.py +0 -0
  261. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/toolbench_static/requirements.txt +0 -0
  262. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/third_party/toolbench_static/toolbench_static.py +0 -0
  263. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/tools/__init__.py +0 -0
  264. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/tools/combine_reports.py +0 -0
  265. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/tools/gen_mmlu_subject_mapping.py +0 -0
  266. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/tools/rewrite_eval_results.py +0 -0
  267. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/utils/__init__.py +0 -0
  268. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/utils/arena_utils.py +0 -0
  269. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/utils/completion_parsers.py +0 -0
  270. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/utils/logger.py +0 -0
  271. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/utils/task_cfg_parser.py +0 -0
  272. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/utils/task_utils.py +0 -0
  273. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope/utils/utils.py +0 -0
  274. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope.egg-info/SOURCES.txt +0 -0
  275. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope.egg-info/dependency_links.txt +0 -0
  276. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope.egg-info/entry_points.txt +0 -0
  277. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope.egg-info/not-zip-safe +0 -0
  278. {evalscope-0.7.0 → evalscope-0.7.1}/evalscope.egg-info/top_level.txt +0 -0
  279. {evalscope-0.7.0 → evalscope-0.7.1}/requirements/docs.txt +0 -0
  280. {evalscope-0.7.0 → evalscope-0.7.1}/requirements/framework.txt +0 -0
  281. {evalscope-0.7.0 → evalscope-0.7.1}/requirements/inner.txt +0 -0
  282. {evalscope-0.7.0 → evalscope-0.7.1}/requirements/perf.txt +0 -0
  283. {evalscope-0.7.0 → evalscope-0.7.1}/requirements/rag.txt +0 -0
  284. {evalscope-0.7.0 → evalscope-0.7.1}/requirements/tests.txt +0 -0
  285. {evalscope-0.7.0 → evalscope-0.7.1}/requirements/vlmeval.txt +0 -0
  286. {evalscope-0.7.0 → evalscope-0.7.1}/requirements.txt +0 -0
  287. {evalscope-0.7.0 → evalscope-0.7.1}/setup.cfg +0 -0
  288. {evalscope-0.7.0 → evalscope-0.7.1}/setup.py +0 -0
  289. {evalscope-0.7.0 → evalscope-0.7.1}/tests/__init__.py +0 -0
  290. {evalscope-0.7.0 → evalscope-0.7.1}/tests/cli/__init__.py +0 -0
  291. {evalscope-0.7.0 → evalscope-0.7.1}/tests/cli/test_run.py +0 -0
  292. {evalscope-0.7.0 → evalscope-0.7.1}/tests/perf/__init__.py +0 -0
  293. {evalscope-0.7.0 → evalscope-0.7.1}/tests/perf/test_perf.py +0 -0
  294. {evalscope-0.7.0 → evalscope-0.7.1}/tests/rag/__init__.py +0 -0
  295. {evalscope-0.7.0 → evalscope-0.7.1}/tests/rag/test_clip_benchmark.py +0 -0
  296. {evalscope-0.7.0 → evalscope-0.7.1}/tests/rag/test_mteb.py +0 -0
  297. {evalscope-0.7.0 → evalscope-0.7.1}/tests/rag/test_ragas.py +0 -0
  298. {evalscope-0.7.0 → evalscope-0.7.1}/tests/swift/__init__.py +0 -0
  299. {evalscope-0.7.0 → evalscope-0.7.1}/tests/swift/test_run_swift_eval.py +0 -0
  300. {evalscope-0.7.0 → evalscope-0.7.1}/tests/swift/test_run_swift_vlm_eval.py +0 -0
  301. {evalscope-0.7.0 → evalscope-0.7.1}/tests/swift/test_run_swift_vlm_jugde_eval.py +0 -0
  302. {evalscope-0.7.0 → evalscope-0.7.1}/tests/test_run_all.py +0 -0
  303. {evalscope-0.7.0 → evalscope-0.7.1}/tests/vlm/__init__.py +0 -0
  304. {evalscope-0.7.0 → evalscope-0.7.1}/tests/vlm/test_vlmeval.py +0 -0
{evalscope-0.7.0/evalscope.egg-info → evalscope-0.7.1}/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: evalscope
3
- Version: 0.7.0
3
+ Version: 0.7.1
4
4
  Summary: EvalScope: Lightweight LLMs Evaluation Framework
5
5
  Home-page: https://github.com/modelscope/evalscope
6
6
  Author: ModelScope team
@@ -49,7 +49,7 @@ Requires-Dist: tqdm
49
49
  Requires-Dist: transformers>=4.33
50
50
  Requires-Dist: transformers_stream_generator
51
51
  Provides-Extra: opencompass
52
- Requires-Dist: ms-opencompass>=0.1.3; extra == "opencompass"
52
+ Requires-Dist: ms-opencompass>=0.1.4; extra == "opencompass"
53
53
  Provides-Extra: vlmeval
54
54
  Requires-Dist: ms-vlmeval>=0.0.9; extra == "vlmeval"
55
55
  Provides-Extra: rag
@@ -123,7 +123,7 @@ Requires-Dist: torch; extra == "all"
123
123
  Requires-Dist: tqdm; extra == "all"
124
124
  Requires-Dist: transformers>=4.33; extra == "all"
125
125
  Requires-Dist: transformers_stream_generator; extra == "all"
126
- Requires-Dist: ms-opencompass>=0.1.3; extra == "all"
126
+ Requires-Dist: ms-opencompass>=0.1.4; extra == "all"
127
127
  Requires-Dist: ms-vlmeval>=0.0.9; extra == "all"
128
128
  Requires-Dist: mteb==1.19.4; extra == "all"
129
129
  Requires-Dist: ragas==0.2.5; extra == "all"
{evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/opencompass/tasks/eval_api.py RENAMED
@@ -6,7 +6,8 @@ from opencompass.tasks import OpenICLInferTask
6
6
 
7
7
 
8
8
  with read_base():
9
- from opencompass.configs.summarizers.medium import summarizer
9
+ # from opencompass.configs.summarizers.medium import summarizer
10
+ # from opencompass.configs.summarizers.PMMEval import summarizer
10
11
  from evalscope.backend.opencompass.tasks.eval_datasets import datasets
11
12
 
12
13
  # 1. Get datasets
{evalscope-0.7.0 → evalscope-0.7.1}/evalscope/backend/opencompass/tasks/eval_datasets.py RENAMED
@@ -51,6 +51,7 @@ with read_base():
51
51
  from opencompass.configs.datasets.triviaqa.triviaqa_gen_2121ce import triviaqa_datasets
52
52
  from opencompass.configs.datasets.cmb.cmb_gen_dfb5c4 import cmb_datasets
53
53
  from opencompass.configs.datasets.cmmlu.cmmlu_gen_c13365 import cmmlu_datasets
54
+ from opencompass.configs.datasets.PMMEval.pmmeval_gen import PMMEval_datasets
54
55
 
55
56
  # Note: to be supported
56
57
  # from opencompass.configs.datasets.flores.flores_gen_806ede import flores_datasets
evalscope-0.7.1/evalscope/version.py ADDED
@@ -0,0 +1,4 @@
1
+ # Copyright (c) Alibaba, Inc. and its affiliates.
2
+
3
+ __version__ = "0.7.1"
4
+ __release_datetime__ = "2024-11-29 03:00:00"
{evalscope-0.7.0 → evalscope-0.7.1/evalscope.egg-info}/PKG-INFO RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: evalscope
3
- Version: 0.7.0
3
+ Version: 0.7.1
4
4
  Summary: EvalScope: Lightweight LLMs Evaluation Framework
5
5
  Home-page: https://github.com/modelscope/evalscope
6
6
  Author: ModelScope team
@@ -49,7 +49,7 @@ Requires-Dist: tqdm
49
49
  Requires-Dist: transformers>=4.33
50
50
  Requires-Dist: transformers_stream_generator
51
51
  Provides-Extra: opencompass
52
- Requires-Dist: ms-opencompass>=0.1.3; extra == "opencompass"
52
+ Requires-Dist: ms-opencompass>=0.1.4; extra == "opencompass"
53
53
  Provides-Extra: vlmeval
54
54
  Requires-Dist: ms-vlmeval>=0.0.9; extra == "vlmeval"
55
55
  Provides-Extra: rag
@@ -123,7 +123,7 @@ Requires-Dist: torch; extra == "all"
123
123
  Requires-Dist: tqdm; extra == "all"
124
124
  Requires-Dist: transformers>=4.33; extra == "all"
125
125
  Requires-Dist: transformers_stream_generator; extra == "all"
126
- Requires-Dist: ms-opencompass>=0.1.3; extra == "all"
126
+ Requires-Dist: ms-opencompass>=0.1.4; extra == "all"
127
127
  Requires-Dist: ms-vlmeval>=0.0.9; extra == "all"
128
128
  Requires-Dist: mteb==1.19.4; extra == "all"
129
129
  Requires-Dist: ragas==0.2.5; extra == "all"
{evalscope-0.7.0 → evalscope-0.7.1}/evalscope.egg-info/requires.txt RENAMED
@@ -64,7 +64,7 @@ torch
64
64
  tqdm
65
65
  transformers>=4.33
66
66
  transformers_stream_generator
67
- ms-opencompass>=0.1.3
67
+ ms-opencompass>=0.1.4
68
68
  ms-vlmeval>=0.0.9
69
69
  mteb==1.19.4
70
70
  ragas==0.2.5
@@ -104,7 +104,7 @@ transformers<4.43,>=4.33
104
104
  transformers_stream_generator
105
105
 
106
106
  [opencompass]
107
- ms-opencompass>=0.1.3
107
+ ms-opencompass>=0.1.4
108
108
 
109
109
  [perf]
110
110
  aiohttp
evalscope-0.7.1/requirements/opencompass.txt ADDED
@@ -0,0 +1 @@
1
+ ms-opencompass>=0.1.4
evalscope-0.7.0/evalscope/version.py DELETED
@@ -1,4 +0,0 @@
1
- # Copyright (c) Alibaba, Inc. and its affiliates.
2
-
3
- __version__ = "0.7.0"
4
- __release_datetime__ = "2024-11-28 15:00:00"
evalscope-0.7.0/requirements/opencompass.txt DELETED
@@ -1 +0,0 @@
1
- ms-opencompass>=0.1.3
{evalscope-0.7.0 → evalscope-0.7.1}/LICENSE RENAMED
File without changes
{evalscope-0.7.0 → evalscope-0.7.1}/MANIFEST.in RENAMED
File without changes
{evalscope-0.7.0 → evalscope-0.7.1}/README.md RENAMED
File without changes
{evalscope-0.7.0 → evalscope-0.7.1}/evalscope/cache.py RENAMED
File without changes
{evalscope-0.7.0 → evalscope-0.7.1}/evalscope/config.py RENAMED
File without changes