evalscope 0.5.0__py3-none-any.whl

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.
Files changed (165) hide show
  1. evalscope/__init__.py +3 -0
  2. evalscope/backend/__init__.py +3 -0
  3. evalscope/backend/base.py +27 -0
  4. evalscope/backend/opencompass/__init__.py +3 -0
  5. evalscope/backend/opencompass/api_meta_template.py +64 -0
  6. evalscope/backend/opencompass/backend_manager.py +247 -0
  7. evalscope/backend/opencompass/tasks/__init__.py +1 -0
  8. evalscope/backend/opencompass/tasks/eval_api.py +30 -0
  9. evalscope/backend/opencompass/tasks/eval_datasets.py +71 -0
  10. evalscope/backend/vlm_eval_kit/__init__.py +1 -0
  11. evalscope/backend/vlm_eval_kit/backend_manager.py +153 -0
  12. evalscope/benchmarks/__init__.py +4 -0
  13. evalscope/benchmarks/arc/__init__.py +5 -0
  14. evalscope/benchmarks/arc/ai2_arc.py +148 -0
  15. evalscope/benchmarks/arc/arc_adapter.py +231 -0
  16. evalscope/benchmarks/bbh/__init__.py +6 -0
  17. evalscope/benchmarks/bbh/bbh_adapter.py +308 -0
  18. evalscope/benchmarks/bbh/cot_prompts/boolean_expressions.txt +23 -0
  19. evalscope/benchmarks/bbh/cot_prompts/causal_judgement.txt +25 -0
  20. evalscope/benchmarks/bbh/cot_prompts/date_understanding.txt +33 -0
  21. evalscope/benchmarks/bbh/cot_prompts/disambiguation_qa.txt +37 -0
  22. evalscope/benchmarks/bbh/cot_prompts/dyck_languages.txt +72 -0
  23. evalscope/benchmarks/bbh/cot_prompts/formal_fallacies.txt +44 -0
  24. evalscope/benchmarks/bbh/cot_prompts/geometric_shapes.txt +78 -0
  25. evalscope/benchmarks/bbh/cot_prompts/hyperbaton.txt +28 -0
  26. evalscope/benchmarks/bbh/cot_prompts/logical_deduction_five_objects.txt +37 -0
  27. evalscope/benchmarks/bbh/cot_prompts/logical_deduction_seven_objects.txt +37 -0
  28. evalscope/benchmarks/bbh/cot_prompts/logical_deduction_three_objects.txt +37 -0
  29. evalscope/benchmarks/bbh/cot_prompts/movie_recommendation.txt +42 -0
  30. evalscope/benchmarks/bbh/cot_prompts/multistep_arithmetic_two.txt +25 -0
  31. evalscope/benchmarks/bbh/cot_prompts/navigate.txt +43 -0
  32. evalscope/benchmarks/bbh/cot_prompts/object_counting.txt +37 -0
  33. evalscope/benchmarks/bbh/cot_prompts/penguins_in_a_table.txt +41 -0
  34. evalscope/benchmarks/bbh/cot_prompts/reasoning_about_colored_objects.txt +63 -0
  35. evalscope/benchmarks/bbh/cot_prompts/ruin_names.txt +44 -0
  36. evalscope/benchmarks/bbh/cot_prompts/salient_translation_error_detection.txt +40 -0
  37. evalscope/benchmarks/bbh/cot_prompts/snarks.txt +30 -0
  38. evalscope/benchmarks/bbh/cot_prompts/sports_understanding.txt +10 -0
  39. evalscope/benchmarks/bbh/cot_prompts/temporal_sequences.txt +77 -0
  40. evalscope/benchmarks/bbh/cot_prompts/tracking_shuffled_objects_five_objects.txt +40 -0
  41. evalscope/benchmarks/bbh/cot_prompts/tracking_shuffled_objects_seven_objects.txt +40 -0
  42. evalscope/benchmarks/bbh/cot_prompts/tracking_shuffled_objects_three_objects.txt +40 -0
  43. evalscope/benchmarks/bbh/cot_prompts/web_of_lies.txt +28 -0
  44. evalscope/benchmarks/bbh/cot_prompts/word_sorting.txt +17 -0
  45. evalscope/benchmarks/benchmark.py +65 -0
  46. evalscope/benchmarks/ceval/__init__.py +5 -0
  47. evalscope/benchmarks/ceval/ceval_adapter.py +340 -0
  48. evalscope/benchmarks/ceval/ceval_exam.py +159 -0
  49. evalscope/benchmarks/cmmlu/__init__.py +5 -0
  50. evalscope/benchmarks/cmmlu/cmmlu.py +166 -0
  51. evalscope/benchmarks/cmmlu/cmmlu_adapter.py +369 -0
  52. evalscope/benchmarks/competition_math/__init__.py +5 -0
  53. evalscope/benchmarks/competition_math/competition_math.py +88 -0
  54. evalscope/benchmarks/competition_math/competition_math_adapter.py +470 -0
  55. evalscope/benchmarks/data_adapter.py +263 -0
  56. evalscope/benchmarks/general_qa/__init__.py +5 -0
  57. evalscope/benchmarks/general_qa/general_qa_adapter.py +186 -0
  58. evalscope/benchmarks/gsm8k/__init__.py +5 -0
  59. evalscope/benchmarks/gsm8k/gsm8k.py +127 -0
  60. evalscope/benchmarks/gsm8k/gsm8k_adapter.py +236 -0
  61. evalscope/benchmarks/hellaswag/__init__.py +5 -0
  62. evalscope/benchmarks/hellaswag/hellaswag.py +116 -0
  63. evalscope/benchmarks/hellaswag/hellaswag_adapter.py +222 -0
  64. evalscope/benchmarks/humaneval/__init__.py +5 -0
  65. evalscope/benchmarks/humaneval/humaneval.py +82 -0
  66. evalscope/benchmarks/humaneval/humaneval_adapter.py +21 -0
  67. evalscope/benchmarks/mmlu/__init__.py +5 -0
  68. evalscope/benchmarks/mmlu/mmlu.py +174 -0
  69. evalscope/benchmarks/mmlu/mmlu_adapter.py +375 -0
  70. evalscope/benchmarks/race/__init__.py +5 -0
  71. evalscope/benchmarks/race/race.py +118 -0
  72. evalscope/benchmarks/race/race_adapter.py +229 -0
  73. evalscope/benchmarks/trivia_qa/__init__.py +5 -0
  74. evalscope/benchmarks/trivia_qa/trivia_qa.py +104 -0
  75. evalscope/benchmarks/trivia_qa/trivia_qa_adapter.py +207 -0
  76. evalscope/benchmarks/truthful_qa/__init__.py +5 -0
  77. evalscope/benchmarks/truthful_qa/truthful_qa.py +167 -0
  78. evalscope/benchmarks/truthful_qa/truthful_qa_adapter.py +351 -0
  79. evalscope/cache.py +98 -0
  80. evalscope/cli/__init__.py +1 -0
  81. evalscope/cli/base.py +20 -0
  82. evalscope/cli/cli.py +26 -0
  83. evalscope/cli/start_perf.py +37 -0
  84. evalscope/cli/start_server.py +138 -0
  85. evalscope/config.py +165 -0
  86. evalscope/constants.py +150 -0
  87. evalscope/evaluator/__init__.py +3 -0
  88. evalscope/evaluator/evaluator.py +689 -0
  89. evalscope/evaluator/rating_eval.py +178 -0
  90. evalscope/evaluator/reviewer/__init__.py +1 -0
  91. evalscope/evaluator/reviewer/auto_reviewer.py +411 -0
  92. evalscope/metrics/__init__.py +1 -0
  93. evalscope/metrics/bundled_rouge_score/__init__.py +14 -0
  94. evalscope/metrics/bundled_rouge_score/rouge_scorer.py +342 -0
  95. evalscope/metrics/code_metric.py +104 -0
  96. evalscope/metrics/math_accuracy.py +60 -0
  97. evalscope/metrics/metrics.py +405 -0
  98. evalscope/metrics/rouge_metric.py +129 -0
  99. evalscope/models/__init__.py +4 -0
  100. evalscope/models/custom/__init__.py +4 -0
  101. evalscope/models/custom/custom_model.py +53 -0
  102. evalscope/models/dummy_chat_model.py +50 -0
  103. evalscope/models/model.py +88 -0
  104. evalscope/models/model_adapter.py +586 -0
  105. evalscope/models/openai_model.py +103 -0
  106. evalscope/models/template.py +1446 -0
  107. evalscope/perf/__init__.py +0 -0
  108. evalscope/perf/_logging.py +32 -0
  109. evalscope/perf/api_plugin_base.py +60 -0
  110. evalscope/perf/custom_api.py +87 -0
  111. evalscope/perf/dashscope_api.py +84 -0
  112. evalscope/perf/dataset_plugin_base.py +64 -0
  113. evalscope/perf/datasets/__init__.py +0 -0
  114. evalscope/perf/datasets/line_by_line.py +18 -0
  115. evalscope/perf/datasets/longalpaca_12k.py +20 -0
  116. evalscope/perf/datasets/openqa.py +22 -0
  117. evalscope/perf/how_to_analysis_result.py +24 -0
  118. evalscope/perf/http_client.py +756 -0
  119. evalscope/perf/openai_api.py +130 -0
  120. evalscope/perf/plugin_registry.py +35 -0
  121. evalscope/perf/query_parameters.py +42 -0
  122. evalscope/perf/server_sent_event.py +43 -0
  123. evalscope/preprocess/__init__.py +1 -0
  124. evalscope/preprocess/tokenizers/__init__.py +0 -0
  125. evalscope/preprocess/tokenizers/gpt2_tokenizer.py +221 -0
  126. evalscope/registry/__init__.py +1 -0
  127. evalscope/registry/tasks/arc.yaml +29 -0
  128. evalscope/registry/tasks/bbh.yaml +27 -0
  129. evalscope/registry/tasks/bbh_mini.yaml +27 -0
  130. evalscope/registry/tasks/ceval.yaml +27 -0
  131. evalscope/registry/tasks/ceval_mini.yaml +27 -0
  132. evalscope/registry/tasks/cmmlu.yaml +27 -0
  133. evalscope/registry/tasks/eval_qwen-7b-chat_v100.yaml +28 -0
  134. evalscope/registry/tasks/general_qa.yaml +27 -0
  135. evalscope/registry/tasks/gsm8k.yaml +29 -0
  136. evalscope/registry/tasks/mmlu.yaml +29 -0
  137. evalscope/registry/tasks/mmlu_mini.yaml +27 -0
  138. evalscope/run.py +404 -0
  139. evalscope/run_arena.py +204 -0
  140. evalscope/run_ms.py +140 -0
  141. evalscope/summarizer.py +144 -0
  142. evalscope/third_party/__init__.py +1 -0
  143. evalscope/third_party/toolbench_static/__init__.py +3 -0
  144. evalscope/third_party/toolbench_static/eval.py +219 -0
  145. evalscope/third_party/toolbench_static/infer.py +278 -0
  146. evalscope/third_party/toolbench_static/llm/__init__.py +1 -0
  147. evalscope/third_party/toolbench_static/llm/swift_infer.py +45 -0
  148. evalscope/third_party/toolbench_static/toolbench_static.py +50 -0
  149. evalscope/tools/__init__.py +1 -0
  150. evalscope/tools/combine_reports.py +140 -0
  151. evalscope/tools/gen_mmlu_subject_mapping.py +90 -0
  152. evalscope/tools/rewrite_eval_results.py +95 -0
  153. evalscope/utils/__init__.py +4 -0
  154. evalscope/utils/arena_utils.py +247 -0
  155. evalscope/utils/completion_parsers.py +87 -0
  156. evalscope/utils/logger.py +64 -0
  157. evalscope/utils/task_cfg_parser.py +10 -0
  158. evalscope/utils/task_utils.py +19 -0
  159. evalscope/utils/utils.py +625 -0
  160. evalscope/version.py +4 -0
  161. evalscope-0.5.0.dist-info/METADATA +566 -0
  162. evalscope-0.5.0.dist-info/RECORD +165 -0
  163. evalscope-0.5.0.dist-info/WHEEL +5 -0
  164. evalscope-0.5.0.dist-info/entry_points.txt +3 -0
  165. evalscope-0.5.0.dist-info/top_level.txt +1 -0
@@ -0,0 +1,165 @@
1
+ evalscope/__init__.py,sha256=3eLMMrjkAIAs3vGluXNZn5-xTSbO_vfba9yNPbkVtg8,105
2
+ evalscope/cache.py,sha256=zpGjL9JMosqjk_dkODVwvIGiUC0WAMmMTHDNJOvBQU8,3288
3
+ evalscope/config.py,sha256=LfVLET3k7UvZ5nISZJ0uigZetZlvKvaYPfj04dGDblQ,6916
4
+ evalscope/constants.py,sha256=g8lGYlpA4Wk88HwtqId1-jJX_z8Lr2k02gWLsyofyj0,2670
5
+ evalscope/run.py,sha256=T-2zoJpBx6YxLnLJH-iFF3UxUGYTU36PMV_DQ9e8tSM,18484
6
+ evalscope/run_arena.py,sha256=_LL8fqeKUEMUg985TENYzcnH5_Q8sqPxM68eZk-jhLA,8793
7
+ evalscope/run_ms.py,sha256=UtJoGnah64SXigTawJQWTi_TEGjr7Td0rjCTaO-htL8,6028
8
+ evalscope/summarizer.py,sha256=Ie1kwPETpz3x2yROLMGqC0UwEj6OKJuKwEcUqxUx5fM,6358
9
+ evalscope/version.py,sha256=_1Lu_R_3DYpaloS52_vLqUEBtD1ixppLykqr1dl_TqM,118
10
+ evalscope/backend/__init__.py,sha256=UP_TW5KBq6V_Nvqkeb7PGvGGX3rVYussT43npwCwDgE,135
11
+ evalscope/backend/base.py,sha256=5BLrDNNwxsGp35zorD-kphmN15tlBbkuuqwkz8jWZq0,876
12
+ evalscope/backend/opencompass/__init__.py,sha256=UP_TW5KBq6V_Nvqkeb7PGvGGX3rVYussT43npwCwDgE,135
13
+ evalscope/backend/opencompass/api_meta_template.py,sha256=sBW0XbVDOKeJ7mVUDLhmcG4e0yClw3eluazdp_8wtgQ,1753
14
+ evalscope/backend/opencompass/backend_manager.py,sha256=swmJELcEDNorZzyXZxOhz2q5tWAE-IkotqJVZ2rBRQ4,10366
15
+ evalscope/backend/opencompass/tasks/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
16
+ evalscope/backend/opencompass/tasks/eval_api.py,sha256=9ylEm1Xk_xft56EEpVvlzK89_R1kQh7PI6uVZiexqy8,1042
17
+ evalscope/backend/opencompass/tasks/eval_datasets.py,sha256=DWwKcQGGSkkh65H1d-oKN8Jow0Q0cHJJzDC75inycFM,5186
18
+ evalscope/backend/vlm_eval_kit/__init__.py,sha256=xTgHM95lWzh4s0W7zxLwYkgUbPAZfAb0UoGGmyyBXrs,83
19
+ evalscope/backend/vlm_eval_kit/backend_manager.py,sha256=_5yZ7dUULvzLw9-LYg5Svmeia8M6-8CInmiwtGfkYF4,6213
20
+ evalscope/benchmarks/__init__.py,sha256=6TKP35wfKf7R_h870fsEtcIlIAgomKOcukNL9M-5I1Y,162
21
+ evalscope/benchmarks/benchmark.py,sha256=e7rA8Y_vo6q5BhlUbZGWfZ1-SfJnU2IFRg62pnjQtDk,2157
22
+ evalscope/benchmarks/data_adapter.py,sha256=eVQvOQYQOQbIl8UlvOEUqRThL3FP3aUD6DSlqF1bqO0,10395
23
+ evalscope/benchmarks/arc/__init__.py,sha256=7k2jFDUCHpEKDdQZ3Bmq59YmImFg9RyIfZQIsGebhE8,314
24
+ evalscope/benchmarks/arc/ai2_arc.py,sha256=Wim8JsH094og7d0eLCEI0kUwDP_0x7AT117oTRPdiAI,5608
25
+ evalscope/benchmarks/arc/arc_adapter.py,sha256=RpXgp69N-3UinKDAnMVxeuGrOBFX2HgXAwwjm_kH-vg,9214
26
+ evalscope/benchmarks/bbh/__init__.py,sha256=x_FWzYE1gKf0mUswYXOKqKaAkmSm6IfzWvPnCtjbs8I,306
27
+ evalscope/benchmarks/bbh/bbh_adapter.py,sha256=pUUjwtxX_9_z0DUo_oCddc7ktA5enhN5EaNrSRWT4V4,10804
28
+ evalscope/benchmarks/bbh/cot_prompts/boolean_expressions.txt,sha256=hNie8uvyVSF-W0sZW721vEhH7_9lypZ0qtDRVraBgxg,1780
29
+ evalscope/benchmarks/bbh/cot_prompts/causal_judgement.txt,sha256=t2ozSTodp4p2ZibgkhoAomhBFtf2keRioum9QF9E5Sk,3652
30
+ evalscope/benchmarks/bbh/cot_prompts/date_understanding.txt,sha256=7GDstZmMXjlucd6RsN5WzQiLij_VASLHHEx3mMP4wJ8,1166
31
+ evalscope/benchmarks/bbh/cot_prompts/disambiguation_qa.txt,sha256=qhCLqXjtlI325tGCBXgLnM8V_bUKpUW-Dohh7U-BPSY,3567
32
+ evalscope/benchmarks/bbh/cot_prompts/dyck_languages.txt,sha256=Ut7JSNl4zQqeuDt1eq-Mrgdxf2kMar1i85DpVqEi5vU,2404
33
+ evalscope/benchmarks/bbh/cot_prompts/formal_fallacies.txt,sha256=WNruIcuKwCaNwHPj-xs6VK1RzyVq2JDED02MadpDPl4,4476
34
+ evalscope/benchmarks/bbh/cot_prompts/geometric_shapes.txt,sha256=4hn9zfKMo7HquDPsWuy5fEnkuJtsI9GrfabostMLQLo,4830
35
+ evalscope/benchmarks/bbh/cot_prompts/hyperbaton.txt,sha256=Jmv9AxvfpgbLsi0Nc_3_xcSLuwpiT-Po4VgTukmA0w8,3113
36
+ evalscope/benchmarks/bbh/cot_prompts/logical_deduction_five_objects.txt,sha256=LIqVgRhbD1t5ohv5FGW-Ql98kst4mIl-IpX-IY5c6mg,2504
37
+ evalscope/benchmarks/bbh/cot_prompts/logical_deduction_seven_objects.txt,sha256=LIqVgRhbD1t5ohv5FGW-Ql98kst4mIl-IpX-IY5c6mg,2504
38
+ evalscope/benchmarks/bbh/cot_prompts/logical_deduction_three_objects.txt,sha256=LIqVgRhbD1t5ohv5FGW-Ql98kst4mIl-IpX-IY5c6mg,2504
39
+ evalscope/benchmarks/bbh/cot_prompts/movie_recommendation.txt,sha256=gkMO9u025Uc4RClBeQtF11FDcNb9EsxUlrbwGDdllZc,2120
40
+ evalscope/benchmarks/bbh/cot_prompts/multistep_arithmetic_two.txt,sha256=g7Y4iyJ0fQGmWyLYWwzaqlpmaypQ3x2sK49AX_YL3NU,2385
41
+ evalscope/benchmarks/bbh/cot_prompts/navigate.txt,sha256=DATvl8pqWOblx260R3muCt1sYErASv0TAviag1UZrVE,2146
42
+ evalscope/benchmarks/bbh/cot_prompts/object_counting.txt,sha256=pTYwcwnt-yypHJ9hRLyDVW0hMgBPgxUwX6f6TZnFriw,1417
43
+ evalscope/benchmarks/bbh/cot_prompts/penguins_in_a_table.txt,sha256=juEuZ97hBp8vgQl_mkKiAsMdbb5MqxatkMRKkKDvopc,2385
44
+ evalscope/benchmarks/bbh/cot_prompts/reasoning_about_colored_objects.txt,sha256=5KJQPIDdCPkyRmk9riKDHlSFfTtlhyG8aIeTDl7h6JA,2294
45
+ evalscope/benchmarks/bbh/cot_prompts/ruin_names.txt,sha256=OqEgTV80zfH8Mu2_IZkpPMKUREqVWOFSJo6t7D2sUx4,3480
46
+ evalscope/benchmarks/bbh/cot_prompts/salient_translation_error_detection.txt,sha256=nBP1tctGuL8pCBYvH3BNW3nQRrRzY7lFNd5bWG6Hs64,6140
47
+ evalscope/benchmarks/bbh/cot_prompts/snarks.txt,sha256=QSAKws7Of09NdrmFPjJJCVc0zvAIMak6xROhpdgxSt4,3113
48
+ evalscope/benchmarks/bbh/cot_prompts/sports_understanding.txt,sha256=vgTwHu4mowIeCtaaD24fRmfsaU-V9lG1z4U6izcoFBg,820
49
+ evalscope/benchmarks/bbh/cot_prompts/temporal_sequences.txt,sha256=xZeBUTWvnAT3jL8SgQJqiC_a82FfYYcgEra6frIuvlA,3022
50
+ evalscope/benchmarks/bbh/cot_prompts/tracking_shuffled_objects_five_objects.txt,sha256=RmuGDIzsjWNt1ZlkqmerLHiVAWPzZOTVENcgoiM7AZg,2603
51
+ evalscope/benchmarks/bbh/cot_prompts/tracking_shuffled_objects_seven_objects.txt,sha256=RmuGDIzsjWNt1ZlkqmerLHiVAWPzZOTVENcgoiM7AZg,2603
52
+ evalscope/benchmarks/bbh/cot_prompts/tracking_shuffled_objects_three_objects.txt,sha256=RmuGDIzsjWNt1ZlkqmerLHiVAWPzZOTVENcgoiM7AZg,2603
53
+ evalscope/benchmarks/bbh/cot_prompts/web_of_lies.txt,sha256=aPWMXg6mdgoqMao8Oc3jcjeOBh0RUPqN3aBvxaWv9pc,2944
54
+ evalscope/benchmarks/bbh/cot_prompts/word_sorting.txt,sha256=uhRRz8y0hfHI96olJS9IU32XafGcdiqsPPCOexB1hL4,2163
55
+ evalscope/benchmarks/ceval/__init__.py,sha256=SatTco8Ks6wD0jh9LUN5chf21VaJnwW1SG4cGG8OYAo,343
56
+ evalscope/benchmarks/ceval/ceval_adapter.py,sha256=FBUTdmW4a5TY7atBjE_H1h_ST2_WoPWMMTvfHNvusNU,15852
57
+ evalscope/benchmarks/ceval/ceval_exam.py,sha256=S32eMfGUBMrUDP39HzO6XfvSir0tthHCPItNtriE-hc,5063
58
+ evalscope/benchmarks/cmmlu/__init__.py,sha256=mIMlXA_BHb_bF71Oi5XJwhV_sZKN2b_lBTOXhU5h6Bg,342
59
+ evalscope/benchmarks/cmmlu/cmmlu.py,sha256=q_6ONrjdcHNqpXTUmSVbNOfl1yMd0zEQZWnh0PMQmYY,5153
60
+ evalscope/benchmarks/cmmlu/cmmlu_adapter.py,sha256=jqVghYwex2Awx7THgka0wQ7dFY0EdzfnI7n0aMXGPro,15216
61
+ evalscope/benchmarks/competition_math/__init__.py,sha256=hXO0DTtrA_0YDYUcyrL4XOyPGvPEa0sy2miHTF1Cxrg,393
62
+ evalscope/benchmarks/competition_math/competition_math.py,sha256=0p5iKUfU6WpXgplb44YgVWZUYkeWLLmOdj66_dapdDc,2678
63
+ evalscope/benchmarks/competition_math/competition_math_adapter.py,sha256=FijGL1FlEWJAy34tp3bIapiglT7KBJ8AvU8bjP4CGAw,19087
64
+ evalscope/benchmarks/general_qa/__init__.py,sha256=lsGH8AlyH6MNCs7xZhWPKW8Ac3pwZg2hLibWMbyiKAc,346
65
+ evalscope/benchmarks/general_qa/general_qa_adapter.py,sha256=N4Kopo7i3JfEG6Fann-kjPpYXcR2BHfYmtG8aZXfwR0,6097
66
+ evalscope/benchmarks/gsm8k/__init__.py,sha256=4rdHRuEZdDO_WPY3RcLSZCAzgLV7UAOXgOa4cSUhmWs,315
67
+ evalscope/benchmarks/gsm8k/gsm8k.py,sha256=WZ8k4EEMjNWWCxY-Dhs2BSR4EHHqYBViyl_UZIGNu7U,4282
68
+ evalscope/benchmarks/gsm8k/gsm8k_adapter.py,sha256=qpRii4zyWK6nadEYxBPDTdOSwyyotWTf0JIxQSoEy2k,13976
69
+ evalscope/benchmarks/hellaswag/__init__.py,sha256=nSLrBNF18Yqcp8B6IiBGsCYkDS3Xnm0nq_QDyXXSqM0,357
70
+ evalscope/benchmarks/hellaswag/hellaswag.py,sha256=bNOUDpGHtAOAyWrQlMiqEGyp0ePTcpIeYbZH3XaFczI,4690
71
+ evalscope/benchmarks/hellaswag/hellaswag_adapter.py,sha256=4Gf6zvnRAi4YljS7UB9PGxJeT0VSNuvhq8yhYiVmZ34,8557
72
+ evalscope/benchmarks/humaneval/__init__.py,sha256=tBPFexx1c6U1nWMpglJqkQiY2GwKrmpSD_snv_NyRec,335
73
+ evalscope/benchmarks/humaneval/humaneval.py,sha256=oNxRcVkYxlzS18N2JmwSaQb1aTZOVHlZMKwIETjfvNs,3482
74
+ evalscope/benchmarks/humaneval/humaneval_adapter.py,sha256=1YiAvNbWRUcaTu9oGwpDMmvS4_zoHt_bNWmNpzJmo-g,1661
75
+ evalscope/benchmarks/mmlu/__init__.py,sha256=fZicGcLq67XOc5cofGCi6WrV4FdubLupKb7nMdCUQSA,337
76
+ evalscope/benchmarks/mmlu/mmlu.py,sha256=GhjZFOgX5qG041eVrSWggOcRcMyl0oAI_yGXmufwEzc,5256
77
+ evalscope/benchmarks/mmlu/mmlu_adapter.py,sha256=9lg_3s3QjGKC794O-RogU9cdvcCP7_Vp4ve9U9dRhz8,16401
78
+ evalscope/benchmarks/race/__init__.py,sha256=htMZhgk40CsvNF7HXaHeAejUnGbUtU6Nu2yATOiMfaU,337
79
+ evalscope/benchmarks/race/race.py,sha256=giY44Vr6CePdVQxpi0x4CLsaknye47Gdlc_PVqN9VCA,3835
80
+ evalscope/benchmarks/race/race_adapter.py,sha256=3zHfz3tFzCVKoYLtzpGek338ZnIGT7ejq_xSaMxiIjU,9900
81
+ evalscope/benchmarks/trivia_qa/__init__.py,sha256=oslov-n_oV3bhEhrPXLJoQwmHE8_vYR2JTerxoHq29A,351
82
+ evalscope/benchmarks/trivia_qa/trivia_qa.py,sha256=xrebA71r_Ek9NvwkDfsmWTuRCsae2HZEGmTBtZMGwfM,3296
83
+ evalscope/benchmarks/trivia_qa/trivia_qa_adapter.py,sha256=0g0xSWorXiHrZ3PKTqOO6g18kK2tUop1HWaAjmCKRwg,7659
84
+ evalscope/benchmarks/truthful_qa/__init__.py,sha256=4bRdnHOceaEvn20jZj0yLCg5wpOHpzP3LRjkYm5u-Fs,367
85
+ evalscope/benchmarks/truthful_qa/truthful_qa.py,sha256=eOcYBjR7XZ4VFSAY4r1_UUoKXakhR-yzd2I3FiOmlUw,7017
86
+ evalscope/benchmarks/truthful_qa/truthful_qa_adapter.py,sha256=Cavimjnc6NPMC1TDOV4_uI37c3--sILz_VqGiJM_z50,14952
87
+ evalscope/cli/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
88
+ evalscope/cli/base.py,sha256=m1DFlF16L0Lyrn0YNuFj8ByGjVJIoI0jKzAoodIXjRk,404
89
+ evalscope/cli/cli.py,sha256=uZ-qC8WBsLd5-Hn94d43sSGg0UC_12RebSD4ToKjypg,844
90
+ evalscope/cli/start_perf.py,sha256=TL6bMXYl3ln-tfs5uBmzb9x94uxz6f3PBFIt1l7g3VA,994
91
+ evalscope/cli/start_server.py,sha256=ATGLP2TE0aImJNicpehdzBuFlNb50F7KhyL4A_ZSoGU,3885
92
+ evalscope/evaluator/__init__.py,sha256=S6MU1O_iiNAaKxNIhO9MEmdW-BSNf_YH2l6NQ9lxVNo,103
93
+ evalscope/evaluator/evaluator.py,sha256=sWaJ2zkPFkSNuRAGdfhTqgF8nbtL1y55NQYHeBK8MG0,30715
94
+ evalscope/evaluator/rating_eval.py,sha256=cJbkyXIuwFUZoe7ZJZM6eUskNd9zlORgndckuon2OQ8,5768
95
+ evalscope/evaluator/reviewer/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
96
+ evalscope/evaluator/reviewer/auto_reviewer.py,sha256=JycPYti9h1j_8DRcu_rc5U0wkEASHYg-XBqrUUoiO-Q,17054
97
+ evalscope/metrics/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
98
+ evalscope/metrics/code_metric.py,sha256=zK1tpNDZbvmSHt3a_JJ5Y2Hdu2cqeFriy__wUOl2tSw,3462
99
+ evalscope/metrics/math_accuracy.py,sha256=1PCy1VUNYg48JcGy-6SUmUDZNwPeAkMW1QQ_lXomdWw,1988
100
+ evalscope/metrics/metrics.py,sha256=sDZljGiZwgHsFZ5eNi65-3z3BLCdIwWUzPcq2QpKf1k,12545
101
+ evalscope/metrics/rouge_metric.py,sha256=sN0r-sXXc-nJUdFrthQPAv1VFdOCrF6zzIYDKaLSgrU,4522
102
+ evalscope/metrics/bundled_rouge_score/__init__.py,sha256=PwbTdk8168FwDJe_l8XIqDuBgZQooDsP31vj7di05Fs,650
103
+ evalscope/metrics/bundled_rouge_score/rouge_scorer.py,sha256=xSLis-zx1hnHuj_9JI7HuUKMS4ZQsX-D8wECZg4D2bg,11450
104
+ evalscope/models/__init__.py,sha256=zG27J2HSeKPGiAIUE7QLPHEPLyXLsfaDwYI_TDXjpCg,145
105
+ evalscope/models/dummy_chat_model.py,sha256=xE8wcFVSCkvizEJ-B8ojX0Ir01Q5KrN5mapjMQaQtbg,1325
106
+ evalscope/models/model.py,sha256=ZzzVzZHVzuzdt5F1r-rEBT44ZfW9B7R1spsrV-T8nSw,3020
107
+ evalscope/models/model_adapter.py,sha256=_Q3_0d1dMBnS1HxaAjpz-Q7gnzSRQH1hklB608DNct8,22488
108
+ evalscope/models/openai_model.py,sha256=PoQS1FIiWIxp1xBJPV7Bq81LFD9FIT3vAHUvNa22DCc,3452
109
+ evalscope/models/template.py,sha256=Yk7-QnvjiLD0zchSZcaDSLmpW8onIeFpngSwtUOYVPk,56035
110
+ evalscope/models/custom/__init__.py,sha256=K4Ewo7Qrs73-jBuPq4ffxd8hMnttKhic-Zj0amH3wiU,103
111
+ evalscope/models/custom/custom_model.py,sha256=2ivxfGQs5V5HDnQEhTBi5v8KNBxJDbzPVJdNOGo3iSg,1566
112
+ evalscope/perf/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
113
+ evalscope/perf/_logging.py,sha256=v-a1uhqUt8116OEGXa-uhCPNE3mLxBaJZaKo2ReJgp8,1034
114
+ evalscope/perf/api_plugin_base.py,sha256=ieAE-WjJLfgKIz0lDv1TkoKU3oPAW4pMseOJLmuHxCo,2243
115
+ evalscope/perf/custom_api.py,sha256=H2IgM-LMjqXxVhbrtkXuiREb-p14zwMmllgl26a-jgw,3712
116
+ evalscope/perf/dashscope_api.py,sha256=_XUF3czkYdPdVgtP7nqzRxROKxlqDjWs4DQnTyocNvM,3410
117
+ evalscope/perf/dataset_plugin_base.py,sha256=6veUTyZ38W1Iig65vxNV9SfmqrsR8ID_UHgNiUO9Bv4,1814
118
+ evalscope/perf/how_to_analysis_result.py,sha256=UVd_aYJ_7N5hl_wK9oIZig1vSwfgzodxW7XC6IWqbdg,1044
119
+ evalscope/perf/http_client.py,sha256=y5t_LPqrxtYS315iz43-4Wu8wZgkftRgC3UlseSVKR0,34540
120
+ evalscope/perf/openai_api.py,sha256=XrH6jg8VlO9Wu0vGwZna_bHq65XMAlCfCEyqMjs8w1c,5970
121
+ evalscope/perf/plugin_registry.py,sha256=D2MG2AXDBScjuKxB4g_Hg026pSRO752dBimonYtaAzM,782
122
+ evalscope/perf/query_parameters.py,sha256=HfGRZJSzRMVfPezWTvbWhYeprCetGNPX_M_paoDtuOY,1346
123
+ evalscope/perf/server_sent_event.py,sha256=s2UqUr1qAMWzBG1XWCFxhulyztd6FM0tGqVvPC8jD5o,1153
124
+ evalscope/perf/datasets/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
125
+ evalscope/perf/datasets/line_by_line.py,sha256=vbBNh0GcR-BfbFZMT6Z_3NqXe4y-uVfyaoooBRE7gjc,830
126
+ evalscope/perf/datasets/longalpaca_12k.py,sha256=OaOzksyBBbeYwO0tFnKZ6UZ9PQO2RdMRD4HyCVBxnX4,934
127
+ evalscope/perf/datasets/openqa.py,sha256=Dz5__mcYjP81Mc2NCGDAy-JFTVvif1slP7iWQflayFY,1018
128
+ evalscope/preprocess/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
129
+ evalscope/preprocess/tokenizers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
130
+ evalscope/preprocess/tokenizers/gpt2_tokenizer.py,sha256=8dOPVWrzAXhzmzSKBWdWjfDqPlRaMH9slK8v5aWhwcQ,7810
131
+ evalscope/registry/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
132
+ evalscope/registry/tasks/arc.yaml,sha256=phXsBLsAgvHWmU31J89QMnJJnUioRphraQrF9SrJ53c,863
133
+ evalscope/registry/tasks/bbh.yaml,sha256=Ircb_-_eVri2B1MHeSrFs9vIol7RY8ZaWwdz1j57NHA,701
134
+ evalscope/registry/tasks/bbh_mini.yaml,sha256=eZYash__XJcfJau0VqujehuYE2WnFzrWr9s9jCkNT8Q,775
135
+ evalscope/registry/tasks/ceval.yaml,sha256=OoSPrz6c3jPy_T7NH162N1lemwwU2OcnT1zo3S-nPRA,703
136
+ evalscope/registry/tasks/ceval_mini.yaml,sha256=Aw9zzw_6STRVA21mVuAvmGiWCdXzL6ktmdFOCiQWRw4,769
137
+ evalscope/registry/tasks/cmmlu.yaml,sha256=mkTqqXCdc8bqMcCDI_J3d375RaxX_8v4jw5fyAKAW0A,703
138
+ evalscope/registry/tasks/eval_qwen-7b-chat_v100.yaml,sha256=IzPU-edTVDVAr_LGyGoYTlaFvhH1iFp4LpAWKPIy2Lg,737
139
+ evalscope/registry/tasks/general_qa.yaml,sha256=7uiytV5kgs23eP5sBCpg5KXs6b9yFtPFWU1pnCCQIpg,703
140
+ evalscope/registry/tasks/gsm8k.yaml,sha256=KYLK-xtv_3qtgCZiwwP4-rP_ftc_qUmtsl1Tf-jNlCg,730
141
+ evalscope/registry/tasks/mmlu.yaml,sha256=504yhHVfi9pvUBk_SGPs-Yx7R2hx_2_-nAFiGIiFGx4,726
142
+ evalscope/registry/tasks/mmlu_mini.yaml,sha256=wVbosZ5Tm9pwLG5nCphalezXilIjcq5j33nz3MR7_BE,778
143
+ evalscope/third_party/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
144
+ evalscope/third_party/toolbench_static/__init__.py,sha256=BO936RxwodHr4OEpV6W3S_keC91OfOd41_msIJ2d0fs,128
145
+ evalscope/third_party/toolbench_static/eval.py,sha256=TqjMuuYePnD3bGRhQe1_9bIOlAW41kiFSztaEuppRLM,8237
146
+ evalscope/third_party/toolbench_static/infer.py,sha256=WogwVXqDabdcsJ4uftZxAwR2wncp6HYpkS-fACEvjT4,9331
147
+ evalscope/third_party/toolbench_static/toolbench_static.py,sha256=uXvyeyNWTZHFVASnOeMf1sqHUjy9NQ3r8wbkhUQJL1g,1930
148
+ evalscope/third_party/toolbench_static/llm/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
149
+ evalscope/third_party/toolbench_static/llm/swift_infer.py,sha256=UywM8SU2ByFTzD4YkbB17SXJyxmzY1QDwARDuGzbCvs,1452
150
+ evalscope/tools/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
151
+ evalscope/tools/combine_reports.py,sha256=AJYB7ZAHiBu64mcs81bf40ClxukpU2NIUV53UYPiqUs,5388
152
+ evalscope/tools/gen_mmlu_subject_mapping.py,sha256=CUmRdReEU7QfMyprh9I56KmHoRww_zUda_JuyxmCL1A,3277
153
+ evalscope/tools/rewrite_eval_results.py,sha256=ZVi2hVjiTOmR_O5IaLv6qnQNpMz6FnDb95c83Fi3h4I,3193
154
+ evalscope/utils/__init__.py,sha256=6RjACRYUSpGj6fkZ7NzYpl0lFppQCp9KVn5ktZe626s,128
155
+ evalscope/utils/arena_utils.py,sha256=RMkymUv9Cxs37arUntzgDY5P0Dand2jGpsb7uy6wZmg,7670
156
+ evalscope/utils/completion_parsers.py,sha256=61l8CTh1VxHgRoMDhtznpAhuJp47MssGgS-LdEe_h80,2997
157
+ evalscope/utils/logger.py,sha256=Ycd0W17Z_oiByPuPX3_umNrOCHjT9O_e_Kws7ZWUSvU,1855
158
+ evalscope/utils/task_cfg_parser.py,sha256=LiNQ2X8lbZU0cODpaY_PbKyUhNoxZIC495UsLJigX64,138
159
+ evalscope/utils/task_utils.py,sha256=9izZ6H7nso1OJmdoduDpaFN2KA3DmZ91dkKXA8GTIUc,460
160
+ evalscope/utils/utils.py,sha256=zHo9hfxGBUVKE2xNMR7lDoEvfRnk4V4946DEfXQhlq4,20509
161
+ evalscope-0.5.0.dist-info/METADATA,sha256=xMJR-aNm2_br22AlhRWVeu24slq9oW5tXfxOvilPZoM,27367
162
+ evalscope-0.5.0.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
163
+ evalscope-0.5.0.dist-info/entry_points.txt,sha256=eAQqqT7PlGix33BDKmS7wsaIJ_6-vvGrq79Szb6uVxg,57
164
+ evalscope-0.5.0.dist-info/top_level.txt,sha256=jNR-HMn3TR8Atolq7_4rW8IWVX6GhvYV5_1Y_KbJKlY,10
165
+ evalscope-0.5.0.dist-info/RECORD,,
@@ -0,0 +1,5 @@
1
+ Wheel-Version: 1.0
2
+ Generator: bdist_wheel (0.38.4)
3
+ Root-Is-Purelib: true
4
+ Tag: py3-none-any
5
+
@@ -0,0 +1,3 @@
1
+ [console_scripts]
2
+ evalscope = evalscope.cli.cli:run_cmd
3
+
@@ -0,0 +1 @@
1
+ evalscope