evalscope 0.16.2__tar.gz → 0.16.3__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 (495) hide show
  1. {evalscope-0.16.2/evalscope.egg-info → evalscope-0.16.3}/PKG-INFO +1 -1
  2. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/models/adapters/base_adapter.py +0 -2
  3. evalscope-0.16.3/evalscope/version.py +4 -0
  4. {evalscope-0.16.2 → evalscope-0.16.3/evalscope.egg-info}/PKG-INFO +1 -1
  5. {evalscope-0.16.2 → evalscope-0.16.3}/tests/cli/test_run.py +3 -3
  6. evalscope-0.16.2/evalscope/version.py +0 -4
  7. {evalscope-0.16.2 → evalscope-0.16.3}/LICENSE +0 -0
  8. {evalscope-0.16.2 → evalscope-0.16.3}/MANIFEST.in +0 -0
  9. {evalscope-0.16.2 → evalscope-0.16.3}/README.md +0 -0
  10. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/__init__.py +0 -0
  11. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/app/__init__.py +0 -0
  12. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/app/app.py +0 -0
  13. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/app/arguments.py +0 -0
  14. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/app/constants.py +0 -0
  15. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/arguments.py +0 -0
  16. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/__init__.py +0 -0
  17. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/base.py +0 -0
  18. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/opencompass/__init__.py +0 -0
  19. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/opencompass/api_meta_template.py +0 -0
  20. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/opencompass/backend_manager.py +0 -0
  21. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/opencompass/tasks/__init__.py +0 -0
  22. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/opencompass/tasks/eval_api.py +0 -0
  23. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/opencompass/tasks/eval_datasets.py +0 -0
  24. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/__init__.py +0 -0
  25. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/backend_manager.py +0 -0
  26. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/clip_benchmark/__init__.py +0 -0
  27. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/clip_benchmark/arguments.py +0 -0
  28. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/clip_benchmark/dataset_builder.py +0 -0
  29. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/clip_benchmark/task_template.py +0 -0
  30. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/clip_benchmark/tasks/__init__.py +0 -0
  31. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/clip_benchmark/tasks/image_caption.py +0 -0
  32. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/clip_benchmark/tasks/zeroshot_classification.py +0 -0
  33. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/clip_benchmark/tasks/zeroshot_retrieval.py +0 -0
  34. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/clip_benchmark/utils/webdataset_convert.py +0 -0
  35. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/clip_benchmark/utils/webdatasets.txt +0 -0
  36. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/cmteb/__init__.py +0 -0
  37. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/cmteb/arguments.py +0 -0
  38. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/cmteb/base.py +0 -0
  39. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/cmteb/task_template.py +0 -0
  40. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/cmteb/tasks/Classification.py +0 -0
  41. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/cmteb/tasks/Clustering.py +0 -0
  42. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/cmteb/tasks/CustomTask.py +0 -0
  43. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/cmteb/tasks/PairClassification.py +0 -0
  44. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/cmteb/tasks/Reranking.py +0 -0
  45. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/cmteb/tasks/Retrieval.py +0 -0
  46. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/cmteb/tasks/STS.py +0 -0
  47. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/cmteb/tasks/__init__.py +0 -0
  48. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/ragas/__init__.py +0 -0
  49. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/ragas/arguments.py +0 -0
  50. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/ragas/prompts/persona_prompt.py +0 -0
  51. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/ragas/task_template.py +0 -0
  52. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/ragas/tasks/__init__.py +0 -0
  53. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/ragas/tasks/build_distribution.py +0 -0
  54. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/ragas/tasks/build_transform.py +0 -0
  55. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/ragas/tasks/testset_generation.py +0 -0
  56. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/ragas/tasks/translate_prompt.py +0 -0
  57. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/utils/__init__.py +0 -0
  58. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/utils/clip.py +0 -0
  59. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/utils/embedding.py +0 -0
  60. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/utils/llm.py +0 -0
  61. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/rag_eval/utils/tools.py +0 -0
  62. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/vlm_eval_kit/__init__.py +0 -0
  63. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/backend/vlm_eval_kit/backend_manager.py +0 -0
  64. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/__init__.py +0 -0
  65. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/aigc/__init__.py +0 -0
  66. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/aigc/t2i/__init__.py +0 -0
  67. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/aigc/t2i/base.py +0 -0
  68. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/aigc/t2i/evalmuse_adapter.py +0 -0
  69. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/aigc/t2i/genai_bench_adapter.py +0 -0
  70. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/aigc/t2i/general_t2i_adapter.py +0 -0
  71. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/aigc/t2i/hpdv2_adapter.py +0 -0
  72. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/aigc/t2i/tifa_adapter.py +0 -0
  73. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/aime/__init__.py +0 -0
  74. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/aime/aime24_adapter.py +0 -0
  75. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/aime/aime25_adapter.py +0 -0
  76. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/alpaca_eval/__init__.py +0 -0
  77. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/alpaca_eval/alpaca_eval_adapter.py +0 -0
  78. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/arc/__init__.py +0 -0
  79. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/arc/ai2_arc.py +0 -0
  80. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/arc/arc_adapter.py +0 -0
  81. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/arena_hard/__init__.py +0 -0
  82. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/arena_hard/arena_hard_adapter.py +0 -0
  83. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/arena_hard/utils.py +0 -0
  84. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/__init__.py +0 -0
  85. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/bbh_adapter.py +0 -0
  86. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/boolean_expressions.txt +0 -0
  87. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/causal_judgement.txt +0 -0
  88. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/date_understanding.txt +0 -0
  89. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/disambiguation_qa.txt +0 -0
  90. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/dyck_languages.txt +0 -0
  91. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/formal_fallacies.txt +0 -0
  92. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/geometric_shapes.txt +0 -0
  93. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/hyperbaton.txt +0 -0
  94. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/logical_deduction_five_objects.txt +0 -0
  95. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/logical_deduction_seven_objects.txt +0 -0
  96. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/logical_deduction_three_objects.txt +0 -0
  97. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/movie_recommendation.txt +0 -0
  98. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/multistep_arithmetic_two.txt +0 -0
  99. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/navigate.txt +0 -0
  100. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/object_counting.txt +0 -0
  101. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/penguins_in_a_table.txt +0 -0
  102. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/reasoning_about_colored_objects.txt +0 -0
  103. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/ruin_names.txt +0 -0
  104. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/salient_translation_error_detection.txt +0 -0
  105. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/snarks.txt +0 -0
  106. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/sports_understanding.txt +0 -0
  107. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/temporal_sequences.txt +0 -0
  108. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/tracking_shuffled_objects_five_objects.txt +0 -0
  109. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/tracking_shuffled_objects_seven_objects.txt +0 -0
  110. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/tracking_shuffled_objects_three_objects.txt +0 -0
  111. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/web_of_lies.txt +0 -0
  112. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bbh/cot_prompts/word_sorting.txt +0 -0
  113. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/benchmark.py +0 -0
  114. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bfcl/__init__.py +0 -0
  115. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/bfcl/bfcl_adapter.py +0 -0
  116. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/ceval/__init__.py +0 -0
  117. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/ceval/ceval_adapter.py +0 -0
  118. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/ceval/ceval_exam.py +0 -0
  119. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/chinese_simple_qa/__init__.py +0 -0
  120. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/chinese_simple_qa/csimple_qa_adapter.py +0 -0
  121. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/cmmlu/__init__.py +0 -0
  122. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/cmmlu/cmmlu.py +0 -0
  123. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/cmmlu/cmmlu_adapter.py +0 -0
  124. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/cmmlu/samples.jsonl +0 -0
  125. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/competition_math/__init__.py +0 -0
  126. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/competition_math/competition_math.py +0 -0
  127. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/competition_math/competition_math_adapter.py +0 -0
  128. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/data_adapter.py +0 -0
  129. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/data_collection/__init__.py +0 -0
  130. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/data_collection/data_collection_adapter.py +0 -0
  131. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/docmath/__init__.py +0 -0
  132. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/docmath/docmath_adapter.py +0 -0
  133. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/docmath/utils.py +0 -0
  134. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/drop/__init__.py +0 -0
  135. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/drop/drop_adapter.py +0 -0
  136. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/drop/utils.py +0 -0
  137. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/frames/__init__.py +0 -0
  138. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/frames/frames_adapter.py +0 -0
  139. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/frames/utils.py +0 -0
  140. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/general_mcq/__init__.py +0 -0
  141. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/general_mcq/general_mcq_adapter.py +0 -0
  142. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/general_qa/__init__.py +0 -0
  143. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/general_qa/general_qa_adapter.py +0 -0
  144. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/gpqa/__init__.py +0 -0
  145. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/gpqa/chain_of_thought.txt +0 -0
  146. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/gpqa/gpqa_adapter.py +0 -0
  147. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/gsm8k/__init__.py +0 -0
  148. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/gsm8k/gsm8k.py +0 -0
  149. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/gsm8k/gsm8k_adapter.py +0 -0
  150. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/hellaswag/__init__.py +0 -0
  151. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/hellaswag/hellaswag.py +0 -0
  152. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/hellaswag/hellaswag_adapter.py +0 -0
  153. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/humaneval/__init__.py +0 -0
  154. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/humaneval/humaneval.py +0 -0
  155. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/humaneval/humaneval_adapter.py +0 -0
  156. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/ifeval/__init__.py +0 -0
  157. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/ifeval/ifeval_adapter.py +0 -0
  158. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/ifeval/instructions.py +0 -0
  159. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/ifeval/instructions_registry.py +0 -0
  160. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/ifeval/instructions_util.py +0 -0
  161. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/ifeval/utils.py +0 -0
  162. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/iquiz/__init__.py +0 -0
  163. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/iquiz/iquiz_adapter.py +0 -0
  164. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/live_code_bench/__init__.py +0 -0
  165. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/live_code_bench/evaluate_utils.py +0 -0
  166. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/live_code_bench/extract_utils.py +0 -0
  167. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/live_code_bench/live_code_bench_adapter.py +0 -0
  168. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/live_code_bench/load_utils.py +0 -0
  169. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/live_code_bench/pass_k_utils.py +0 -0
  170. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/live_code_bench/prompts.py +0 -0
  171. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/live_code_bench/testing_util.py +0 -0
  172. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/maritime_bench/__init__.py +0 -0
  173. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/maritime_bench/maritime_bench_adapter.py +0 -0
  174. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/math_500/__init__.py +0 -0
  175. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/math_500/math_500_adapter.py +0 -0
  176. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/mmlu/__init__.py +0 -0
  177. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/mmlu/mmlu.py +0 -0
  178. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/mmlu/mmlu_adapter.py +0 -0
  179. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/mmlu/samples.jsonl +0 -0
  180. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/mmlu_pro/__init__.py +0 -0
  181. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/mmlu_pro/mmlu_pro_adapter.py +0 -0
  182. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/mmlu_redux/__init__.py +0 -0
  183. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/mmlu_redux/mmlu_redux_adapter.py +0 -0
  184. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/musr/__init__.py +0 -0
  185. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/musr/musr_adapter.py +0 -0
  186. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/needle_haystack/__init__.py +0 -0
  187. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/needle_haystack/needle_haystack_adapter.py +0 -0
  188. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/needle_haystack/utils.py +0 -0
  189. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/process_bench/__init__.py +0 -0
  190. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/process_bench/critique_template.txt +0 -0
  191. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/process_bench/process_bench_adapter.py +0 -0
  192. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/race/__init__.py +0 -0
  193. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/race/race.py +0 -0
  194. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/race/race_adapter.py +0 -0
  195. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/race/samples.jsonl +0 -0
  196. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/simple_qa/__init__.py +0 -0
  197. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/simple_qa/simple_qa_adapter.py +0 -0
  198. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/super_gpqa/__init__.py +0 -0
  199. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/super_gpqa/five_shot_prompt.txt +0 -0
  200. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/super_gpqa/super_gpqa_adapter.py +0 -0
  201. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/super_gpqa/utils.py +0 -0
  202. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/super_gpqa/zero_shot_prompt.txt +0 -0
  203. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/tool_bench/__init__.py +0 -0
  204. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/tool_bench/tool_bench_adapter.py +0 -0
  205. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/tool_bench/utils.py +0 -0
  206. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/trivia_qa/__init__.py +0 -0
  207. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/trivia_qa/samples.jsonl +0 -0
  208. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/trivia_qa/trivia_qa.py +0 -0
  209. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/trivia_qa/trivia_qa_adapter.py +0 -0
  210. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/truthful_qa/__init__.py +0 -0
  211. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/truthful_qa/truthful_qa.py +0 -0
  212. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/truthful_qa/truthful_qa_adapter.py +0 -0
  213. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/utils.py +0 -0
  214. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/winogrande/__init__.py +0 -0
  215. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/benchmarks/winogrande/winogrande_adapter.py +0 -0
  216. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/cli/__init__.py +0 -0
  217. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/cli/base.py +0 -0
  218. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/cli/cli.py +0 -0
  219. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/cli/start_app.py +0 -0
  220. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/cli/start_eval.py +0 -0
  221. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/cli/start_perf.py +0 -0
  222. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/cli/start_server.py +0 -0
  223. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/collections/__init__.py +0 -0
  224. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/collections/evaluator.py +0 -0
  225. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/collections/sampler.py +0 -0
  226. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/collections/schema.py +0 -0
  227. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/config.py +0 -0
  228. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/constants.py +0 -0
  229. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/evaluator/__init__.py +0 -0
  230. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/evaluator/evaluator.py +0 -0
  231. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/evaluator/rating_eval.py +0 -0
  232. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/evaluator/reviewer/__init__.py +0 -0
  233. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/evaluator/reviewer/auto_reviewer.py +0 -0
  234. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/__init__.py +0 -0
  235. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/bundled_rouge_score/__init__.py +0 -0
  236. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/bundled_rouge_score/rouge_scorer.py +0 -0
  237. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/llm_judge.py +0 -0
  238. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/math_parser.py +0 -0
  239. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/metrics.py +0 -0
  240. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/named_metrics.py +0 -0
  241. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/rouge_metric.py +0 -0
  242. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/__init__.py +0 -0
  243. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/clipscore.py +0 -0
  244. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/constants.py +0 -0
  245. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/itmscore.py +0 -0
  246. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/__init__.py +0 -0
  247. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/clipscore_models/__init__.py +0 -0
  248. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/clipscore_models/build_mps_model/__init__.py +0 -0
  249. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/clipscore_models/build_mps_model/base_model.py +0 -0
  250. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/clipscore_models/build_mps_model/clip_model.py +0 -0
  251. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/clipscore_models/build_mps_model/cross_modeling.py +0 -0
  252. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/clipscore_models/clip_model.py +0 -0
  253. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/clipscore_models/hpsv2_model.py +0 -0
  254. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/clipscore_models/mps_model.py +0 -0
  255. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/clipscore_models/pickscore_model.py +0 -0
  256. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/itmscore_models/__init__.py +0 -0
  257. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/itmscore_models/blip2_itm_model.py +0 -0
  258. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/itmscore_models/fga_blip2_model.py +0 -0
  259. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/itmscore_models/image_reward/ImageReward.py +0 -0
  260. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/itmscore_models/image_reward/__init__.py +0 -0
  261. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/itmscore_models/image_reward/blip_pretrain.py +0 -0
  262. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/itmscore_models/image_reward_model.py +0 -0
  263. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/model.py +0 -0
  264. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/utils.py +0 -0
  265. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/__init__.py +0 -0
  266. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5/__init__.py +0 -0
  267. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5/model/__init__.py +0 -0
  268. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5/model/language_model/clip_t5.py +0 -0
  269. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5/model/multimodal_encoder/builder.py +0 -0
  270. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5/model/multimodal_encoder/clip_encoder.py +0 -0
  271. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5/model/multimodal_projector/builder.py +0 -0
  272. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5_model.py +0 -0
  273. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/gpt4v_model.py +0 -0
  274. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/__init__.py +0 -0
  275. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/config.py +0 -0
  276. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/dist_utils.py +0 -0
  277. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/gradcam.py +0 -0
  278. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/logger.py +0 -0
  279. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/optims.py +0 -0
  280. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/registry.py +0 -0
  281. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/utils.py +0 -0
  282. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/vqa_tools/__init__.py +0 -0
  283. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/vqa_tools/vqa.py +0 -0
  284. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/vqa_tools/vqa_eval.py +0 -0
  285. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/default.yaml +0 -0
  286. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_caption_flant5xl.yaml +0 -0
  287. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_caption_opt2.7b.yaml +0 -0
  288. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_caption_opt6.7b.yaml +0 -0
  289. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_coco.yaml +0 -0
  290. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_instruct_flant5xl.yaml +0 -0
  291. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_instruct_flant5xxl.yaml +0 -0
  292. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_instruct_vicuna13b.yaml +0 -0
  293. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_instruct_vicuna7b.yaml +0 -0
  294. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain.yaml +0 -0
  295. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_flant5xl.yaml +0 -0
  296. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_flant5xl_iter_80k_total_100k_no_prefix.yaml +0 -0
  297. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_flant5xl_iter_80k_total_100k_prefix.yaml +0 -0
  298. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_flant5xl_vitL.yaml +0 -0
  299. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_flant5xxl.yaml +0 -0
  300. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_opt2.7b.yaml +0 -0
  301. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_opt6.7b.yaml +0 -0
  302. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_vitL.yaml +0 -0
  303. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_vicuna13b.yaml +0 -0
  304. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_vicuna7b.yaml +0 -0
  305. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/med_config.json +0 -0
  306. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/med_config_albef.json +0 -0
  307. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/med_large_config.json +0 -0
  308. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/__init__.py +0 -0
  309. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/base_model.py +0 -0
  310. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/Qformer.py +0 -0
  311. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/__init__.py +0 -0
  312. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2.py +0 -0
  313. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2_image_text_matching.py +0 -0
  314. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2_qformer.py +0 -0
  315. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2_t5.py +0 -0
  316. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2_t5_instruct.py +0 -0
  317. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/fga_blip2.py +0 -0
  318. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/modeling_llama.py +0 -0
  319. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/modeling_t5.py +0 -0
  320. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/__init__.py +0 -0
  321. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip.py +0 -0
  322. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_caption.py +0 -0
  323. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_classification.py +0 -0
  324. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_feature_extractor.py +0 -0
  325. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_image_text_matching.py +0 -0
  326. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_nlvr.py +0 -0
  327. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_outputs.py +0 -0
  328. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_pretrain.py +0 -0
  329. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_vqa.py +0 -0
  330. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/nlvr_encoder.py +0 -0
  331. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/clip_vit.py +0 -0
  332. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/eva_vit.py +0 -0
  333. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/med.py +0 -0
  334. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/vit.py +0 -0
  335. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/processors/__init__.py +0 -0
  336. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/processors/base_processor.py +0 -0
  337. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/processors/blip_processors.py +0 -0
  338. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/processors/randaugment.py +0 -0
  339. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/mm_utils.py +0 -0
  340. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/models/vqascore_models/vqa_model.py +0 -0
  341. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/score.py +0 -0
  342. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/metrics/t2v_metrics/vqascore.py +0 -0
  343. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/models/__init__.py +0 -0
  344. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/models/adapters/__init__.py +0 -0
  345. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/models/adapters/bfcl_adapter.py +0 -0
  346. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/models/adapters/chat_adapter.py +0 -0
  347. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/models/adapters/choice_adapter.py +0 -0
  348. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/models/adapters/custom_adapter.py +0 -0
  349. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/models/adapters/server_adapter.py +0 -0
  350. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/models/adapters/t2i_adapter.py +0 -0
  351. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/models/custom/__init__.py +0 -0
  352. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/models/custom/custom_model.py +0 -0
  353. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/models/custom/dummy_model.py +0 -0
  354. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/models/local_model.py +0 -0
  355. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/models/model.py +0 -0
  356. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/models/register.py +0 -0
  357. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/__init__.py +0 -0
  358. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/arguments.py +0 -0
  359. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/benchmark.py +0 -0
  360. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/http_client.py +0 -0
  361. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/main.py +0 -0
  362. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/plugin/__init__.py +0 -0
  363. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/plugin/api/__init__.py +0 -0
  364. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/plugin/api/base.py +0 -0
  365. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/plugin/api/custom_api.py +0 -0
  366. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/plugin/api/dashscope_api.py +0 -0
  367. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/plugin/api/openai_api.py +0 -0
  368. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/plugin/datasets/__init__.py +0 -0
  369. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/plugin/datasets/base.py +0 -0
  370. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/plugin/datasets/custom.py +0 -0
  371. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/plugin/datasets/flickr8k.py +0 -0
  372. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/plugin/datasets/line_by_line.py +0 -0
  373. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/plugin/datasets/longalpaca.py +0 -0
  374. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/plugin/datasets/openqa.py +0 -0
  375. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/plugin/datasets/random_dataset.py +0 -0
  376. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/plugin/datasets/speed_benchmark.py +0 -0
  377. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/plugin/registry.py +0 -0
  378. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/utils/__init__.py +0 -0
  379. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/utils/analysis_result.py +0 -0
  380. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/utils/benchmark_util.py +0 -0
  381. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/utils/db_util.py +0 -0
  382. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/utils/handler.py +0 -0
  383. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/utils/local_server.py +0 -0
  384. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/utils/log_utils.py +0 -0
  385. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/perf/utils/rich_display.py +0 -0
  386. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/registry/__init__.py +0 -0
  387. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/registry/config/cfg_arena.yaml +0 -0
  388. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/registry/config/cfg_arena_zhihu.yaml +0 -0
  389. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/registry/config/cfg_pairwise_baseline.yaml +0 -0
  390. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/registry/config/cfg_single.yaml +0 -0
  391. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/registry/data/prompt_template/lmsys_v2.jsonl +0 -0
  392. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/registry/data/prompt_template/prompt_templates.jsonl +0 -0
  393. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/registry/data/qa_browser/battle.jsonl +0 -0
  394. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/registry/data/qa_browser/category_mapping.yaml +0 -0
  395. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/registry/data/question.jsonl +0 -0
  396. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/registry/tasks/arc.yaml +0 -0
  397. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/registry/tasks/bbh.yaml +0 -0
  398. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/registry/tasks/bbh_mini.yaml +0 -0
  399. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/registry/tasks/ceval.yaml +0 -0
  400. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/registry/tasks/ceval_mini.yaml +0 -0
  401. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/registry/tasks/cmmlu.yaml +0 -0
  402. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/registry/tasks/eval_qwen-7b-chat_v100.yaml +0 -0
  403. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/registry/tasks/general_qa.yaml +0 -0
  404. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/registry/tasks/gsm8k.yaml +0 -0
  405. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/registry/tasks/mmlu.yaml +0 -0
  406. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/registry/tasks/mmlu_mini.yaml +0 -0
  407. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/report/__init__.py +0 -0
  408. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/report/combinator.py +0 -0
  409. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/report/generator.py +0 -0
  410. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/report/utils.py +0 -0
  411. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/run.py +0 -0
  412. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/run_arena.py +0 -0
  413. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/summarizer.py +0 -0
  414. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/__init__.py +0 -0
  415. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/longbench_write/README.md +0 -0
  416. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/longbench_write/__init__.py +0 -0
  417. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/longbench_write/default_task.json +0 -0
  418. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/longbench_write/default_task.yaml +0 -0
  419. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/longbench_write/eval.py +0 -0
  420. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/longbench_write/infer.py +0 -0
  421. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/longbench_write/longbench_write.py +0 -0
  422. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/longbench_write/resources/__init__.py +0 -0
  423. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/longbench_write/resources/judge.txt +0 -0
  424. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/longbench_write/resources/longbench_write.jsonl +0 -0
  425. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/longbench_write/resources/longbench_write_en.jsonl +0 -0
  426. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/longbench_write/resources/longwrite_ruler.jsonl +0 -0
  427. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/longbench_write/tools/__init__.py +0 -0
  428. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/longbench_write/tools/data_etl.py +0 -0
  429. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/longbench_write/tools/openai_api.py +0 -0
  430. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/longbench_write/utils.py +0 -0
  431. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/thinkbench/__init__.py +0 -0
  432. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/thinkbench/eval.py +0 -0
  433. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/thinkbench/infer.py +0 -0
  434. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/thinkbench/resources/critique_template.txt +0 -0
  435. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/thinkbench/resources/reformat_template.txt +0 -0
  436. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/thinkbench/tools/__init__.py +0 -0
  437. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/thinkbench/tools/llm.py +0 -0
  438. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/thinkbench/tools/utils.py +0 -0
  439. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/toolbench_static/README.md +0 -0
  440. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/toolbench_static/__init__.py +0 -0
  441. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/toolbench_static/config_default.json +0 -0
  442. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/toolbench_static/config_default.yaml +0 -0
  443. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/toolbench_static/eval.py +0 -0
  444. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/toolbench_static/infer.py +0 -0
  445. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/toolbench_static/llm/__init__.py +0 -0
  446. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/toolbench_static/llm/swift_infer.py +0 -0
  447. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/toolbench_static/requirements.txt +0 -0
  448. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/third_party/toolbench_static/toolbench_static.py +0 -0
  449. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/utils/__init__.py +0 -0
  450. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/utils/arena_utils.py +0 -0
  451. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/utils/chat_service.py +0 -0
  452. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/utils/completion_parsers.py +0 -0
  453. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/utils/deprecation_utils.py +0 -0
  454. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/utils/filters.py +0 -0
  455. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/utils/import_utils.py +0 -0
  456. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/utils/io_utils.py +0 -0
  457. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/utils/logger.py +0 -0
  458. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/utils/model_utils.py +0 -0
  459. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope/utils/utils.py +0 -0
  460. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope.egg-info/SOURCES.txt +0 -0
  461. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope.egg-info/dependency_links.txt +0 -0
  462. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope.egg-info/entry_points.txt +0 -0
  463. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope.egg-info/not-zip-safe +0 -0
  464. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope.egg-info/requires.txt +0 -0
  465. {evalscope-0.16.2 → evalscope-0.16.3}/evalscope.egg-info/top_level.txt +0 -0
  466. {evalscope-0.16.2 → evalscope-0.16.3}/requirements/aigc.txt +0 -0
  467. {evalscope-0.16.2 → evalscope-0.16.3}/requirements/app.txt +0 -0
  468. {evalscope-0.16.2 → evalscope-0.16.3}/requirements/docs.txt +0 -0
  469. {evalscope-0.16.2 → evalscope-0.16.3}/requirements/framework.txt +0 -0
  470. {evalscope-0.16.2 → evalscope-0.16.3}/requirements/opencompass.txt +0 -0
  471. {evalscope-0.16.2 → evalscope-0.16.3}/requirements/perf.txt +0 -0
  472. {evalscope-0.16.2 → evalscope-0.16.3}/requirements/rag.txt +0 -0
  473. {evalscope-0.16.2 → evalscope-0.16.3}/requirements/vlmeval.txt +0 -0
  474. {evalscope-0.16.2 → evalscope-0.16.3}/requirements.txt +0 -0
  475. {evalscope-0.16.2 → evalscope-0.16.3}/setup.cfg +0 -0
  476. {evalscope-0.16.2 → evalscope-0.16.3}/setup.py +0 -0
  477. {evalscope-0.16.2 → evalscope-0.16.3}/tests/__init__.py +0 -0
  478. {evalscope-0.16.2 → evalscope-0.16.3}/tests/aigc/__init__.py +0 -0
  479. {evalscope-0.16.2 → evalscope-0.16.3}/tests/aigc/test_t2i.py +0 -0
  480. {evalscope-0.16.2 → evalscope-0.16.3}/tests/cli/__init__.py +0 -0
  481. {evalscope-0.16.2 → evalscope-0.16.3}/tests/cli/test_all.py +0 -0
  482. {evalscope-0.16.2 → evalscope-0.16.3}/tests/cli/test_collection.py +0 -0
  483. {evalscope-0.16.2 → evalscope-0.16.3}/tests/perf/__init__.py +0 -0
  484. {evalscope-0.16.2 → evalscope-0.16.3}/tests/perf/test_perf.py +0 -0
  485. {evalscope-0.16.2 → evalscope-0.16.3}/tests/rag/__init__.py +0 -0
  486. {evalscope-0.16.2 → evalscope-0.16.3}/tests/rag/test_clip_benchmark.py +0 -0
  487. {evalscope-0.16.2 → evalscope-0.16.3}/tests/rag/test_mteb.py +0 -0
  488. {evalscope-0.16.2 → evalscope-0.16.3}/tests/rag/test_ragas.py +0 -0
  489. {evalscope-0.16.2 → evalscope-0.16.3}/tests/swift/__init__.py +0 -0
  490. {evalscope-0.16.2 → evalscope-0.16.3}/tests/swift/test_run_swift_eval.py +0 -0
  491. {evalscope-0.16.2 → evalscope-0.16.3}/tests/swift/test_run_swift_vlm_eval.py +0 -0
  492. {evalscope-0.16.2 → evalscope-0.16.3}/tests/swift/test_run_swift_vlm_jugde_eval.py +0 -0
  493. {evalscope-0.16.2 → evalscope-0.16.3}/tests/test_run_all.py +0 -0
  494. {evalscope-0.16.2 → evalscope-0.16.3}/tests/vlm/__init__.py +0 -0
  495. {evalscope-0.16.2 → evalscope-0.16.3}/tests/vlm/test_vlmeval.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: evalscope
3
- Version: 0.16.2
3
+ Version: 0.16.3
4
4
  Summary: EvalScope: Lightweight LLMs Evaluation Framework
5
5
  Home-page: https://github.com/modelscope/evalscope
6
6
  Author: ModelScope team
@@ -54,8 +54,6 @@ def initialize_model_adapter(task_cfg: 'TaskConfig', benchmark: 'DataAdapter', b
54
54
 
55
55
  if 'server' not in model_adapter_cls_str:
56
56
  model_adapter_cls_str = 'server'
57
- logger.info(
58
- f'Using {model_adapter_cls.__name__} for api model evaluation for benchmark {benchmark.name}.')
59
57
 
60
58
  # init server model adapter
61
59
  model_adapter_cls = get_model_adapter(model_adapter_cls_str)
@@ -0,0 +1,4 @@
1
+ # Copyright (c) Alibaba, Inc. and its affiliates.
2
+
3
+ __version__ = '0.16.3'
4
+ __release_datetime__ = '2025-06-24 12:00:00'
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: evalscope
3
- Version: 0.16.2
3
+ Version: 0.16.3
4
4
  Summary: EvalScope: Lightweight LLMs Evaluation Framework
5
5
  Home-page: https://github.com/modelscope/evalscope
6
6
  Author: ModelScope team
@@ -305,8 +305,8 @@ class TestRun(unittest.TestCase):
305
305
  # 'arc',
306
306
  # 'ceval',
307
307
  # 'hellaswag',
308
- 'general_mcq',
309
- # 'general_qa',
308
+ # 'general_mcq',
309
+ 'general_qa',
310
310
  # 'super_gpqa',
311
311
  # 'mmlu_redux',
312
312
  # 'maritime_bench',
@@ -396,7 +396,7 @@ class TestRun(unittest.TestCase):
396
396
  # 'extra_headers':{'key': 'value'},
397
397
  },
398
398
  ignore_errors=False,
399
- # use_cache='outputs/20250616_153756'
399
+ use_cache='outputs/test_2'
400
400
  )
401
401
 
402
402
  run_task(task_cfg=task_cfg)
@@ -1,4 +0,0 @@
1
- # Copyright (c) Alibaba, Inc. and its affiliates.
2
-
3
- __version__ = '0.16.2'
4
- __release_datetime__ = '2025-06-23 20:00:00'
File without changes
File without changes
File without changes