evalscope 0.17.1__py3-none-any.whl → 1.0.1__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.

Potentially problematic release.

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

Files changed (302) hide show
  1. evalscope/__init__.py +4 -1
  2. evalscope/api/benchmark/__init__.py +3 -0
  3. evalscope/api/benchmark/adapters/__init__.py +5 -0
  4. evalscope/api/benchmark/adapters/default_data_adapter.py +684 -0
  5. evalscope/api/benchmark/adapters/image_edit_adapter.py +82 -0
  6. evalscope/api/benchmark/adapters/multi_choice_adapter.py +83 -0
  7. evalscope/api/benchmark/adapters/text2image_adapter.py +156 -0
  8. evalscope/api/benchmark/adapters/vision_language_adapter.py +6 -0
  9. evalscope/api/benchmark/benchmark.py +356 -0
  10. evalscope/api/benchmark/meta.py +121 -0
  11. evalscope/api/dataset/__init__.py +2 -0
  12. evalscope/api/dataset/dataset.py +349 -0
  13. evalscope/api/dataset/loader.py +262 -0
  14. evalscope/api/dataset/utils.py +143 -0
  15. evalscope/api/evaluator/__init__.py +3 -0
  16. evalscope/api/evaluator/cache.py +378 -0
  17. evalscope/api/evaluator/evaluator.py +56 -0
  18. evalscope/api/evaluator/state.py +275 -0
  19. evalscope/api/filter/__init__.py +1 -0
  20. evalscope/api/filter/filter.py +72 -0
  21. evalscope/api/messages/__init__.py +12 -0
  22. evalscope/api/messages/chat_message.py +243 -0
  23. evalscope/api/messages/content.py +102 -0
  24. evalscope/api/messages/utils.py +35 -0
  25. evalscope/api/metric/__init__.py +2 -0
  26. evalscope/api/metric/metric.py +55 -0
  27. evalscope/api/metric/scorer.py +113 -0
  28. evalscope/api/mixin/__init__.py +1 -0
  29. evalscope/api/mixin/llm_judge_mixin.py +168 -0
  30. evalscope/api/model/__init__.py +12 -0
  31. evalscope/api/model/generate_config.py +155 -0
  32. evalscope/api/model/model.py +386 -0
  33. evalscope/api/model/model_output.py +285 -0
  34. evalscope/api/registry.py +182 -0
  35. evalscope/api/tool/__init__.py +3 -0
  36. evalscope/api/tool/tool_call.py +101 -0
  37. evalscope/api/tool/tool_info.py +173 -0
  38. evalscope/api/tool/utils.py +64 -0
  39. evalscope/app/app.py +3 -0
  40. evalscope/app/ui/app_ui.py +2 -1
  41. evalscope/app/ui/multi_model.py +50 -25
  42. evalscope/app/ui/single_model.py +26 -14
  43. evalscope/app/utils/data_utils.py +43 -27
  44. evalscope/app/utils/env_utils.py +12 -0
  45. evalscope/app/utils/text_utils.py +14 -14
  46. evalscope/app/utils/visualization.py +9 -4
  47. evalscope/arguments.py +7 -10
  48. evalscope/backend/opencompass/api_meta_template.py +2 -1
  49. evalscope/backend/opencompass/backend_manager.py +6 -5
  50. evalscope/backend/rag_eval/clip_benchmark/dataset_builder.py +10 -10
  51. evalscope/backend/rag_eval/clip_benchmark/task_template.py +8 -4
  52. evalscope/backend/rag_eval/ragas/task_template.py +2 -1
  53. evalscope/backend/rag_eval/ragas/tasks/build_distribution.py +2 -1
  54. evalscope/backend/rag_eval/ragas/tasks/build_transform.py +7 -4
  55. evalscope/backend/rag_eval/ragas/tasks/testset_generation.py +2 -1
  56. evalscope/backend/rag_eval/ragas/tasks/translate_prompt.py +2 -1
  57. evalscope/backend/rag_eval/utils/embedding.py +10 -1
  58. evalscope/backend/rag_eval/utils/llm.py +13 -12
  59. evalscope/benchmarks/__init__.py +0 -2
  60. evalscope/benchmarks/aime/aime24_adapter.py +38 -40
  61. evalscope/benchmarks/aime/aime25_adapter.py +34 -40
  62. evalscope/benchmarks/alpaca_eval/alpaca_eval_adapter.py +86 -60
  63. evalscope/benchmarks/arc/arc_adapter.py +34 -147
  64. evalscope/benchmarks/arena_hard/arena_hard_adapter.py +96 -70
  65. evalscope/benchmarks/arena_hard/utils.py +37 -1
  66. evalscope/benchmarks/bbh/bbh_adapter.py +72 -144
  67. evalscope/benchmarks/bfcl/bfcl_adapter.py +188 -171
  68. evalscope/benchmarks/bfcl/generation.py +222 -0
  69. evalscope/benchmarks/ceval/ceval_adapter.py +93 -162
  70. evalscope/benchmarks/chinese_simple_qa/csimple_qa_adapter.py +85 -82
  71. evalscope/benchmarks/cmmlu/cmmlu_adapter.py +34 -125
  72. evalscope/benchmarks/competition_math/competition_math_adapter.py +56 -108
  73. evalscope/benchmarks/data_collection/data_collection_adapter.py +187 -45
  74. evalscope/benchmarks/docmath/docmath_adapter.py +109 -51
  75. evalscope/benchmarks/docmath/utils.py +4 -5
  76. evalscope/benchmarks/drop/drop_adapter.py +88 -40
  77. evalscope/benchmarks/frames/frames_adapter.py +136 -52
  78. evalscope/benchmarks/general_arena/general_arena_adapter.py +140 -98
  79. evalscope/benchmarks/general_arena/utils.py +23 -27
  80. evalscope/benchmarks/general_mcq/general_mcq_adapter.py +40 -101
  81. evalscope/benchmarks/general_qa/general_qa_adapter.py +73 -134
  82. evalscope/benchmarks/gpqa/gpqa_adapter.py +61 -100
  83. evalscope/benchmarks/gpqa/{chain_of_thought.txt → prompt.py} +12 -5
  84. evalscope/benchmarks/gsm8k/gsm8k_adapter.py +62 -142
  85. evalscope/benchmarks/hellaswag/hellaswag_adapter.py +35 -124
  86. evalscope/benchmarks/hle/hle_adapter.py +127 -93
  87. evalscope/benchmarks/humaneval/humaneval_adapter.py +86 -55
  88. evalscope/benchmarks/ifeval/ifeval_adapter.py +69 -40
  89. evalscope/benchmarks/ifeval/instructions.py +109 -64
  90. evalscope/benchmarks/ifeval/instructions_registry.py +1 -1
  91. evalscope/benchmarks/ifeval/instructions_util.py +2 -3
  92. evalscope/benchmarks/ifeval/utils.py +6 -7
  93. evalscope/benchmarks/image_edit/gedit/__init__.py +0 -0
  94. evalscope/benchmarks/image_edit/gedit/gedit_adapter.py +138 -0
  95. evalscope/benchmarks/image_edit/gedit/utils.py +372 -0
  96. evalscope/benchmarks/image_edit/gedit/vie_prompts.py +406 -0
  97. evalscope/benchmarks/iquiz/iquiz_adapter.py +30 -65
  98. evalscope/benchmarks/live_code_bench/evaluate_utils.py +2 -2
  99. evalscope/benchmarks/live_code_bench/live_code_bench_adapter.py +121 -71
  100. evalscope/benchmarks/live_code_bench/load_utils.py +13 -21
  101. evalscope/benchmarks/live_code_bench/testing_util.py +6 -2
  102. evalscope/benchmarks/maritime_bench/maritime_bench_adapter.py +49 -75
  103. evalscope/benchmarks/math_500/math_500_adapter.py +41 -48
  104. evalscope/benchmarks/math_vista/__init__.py +0 -0
  105. evalscope/benchmarks/math_vista/math_vista_adapter.py +129 -0
  106. evalscope/benchmarks/mmlu/mmlu_adapter.py +32 -205
  107. evalscope/benchmarks/mmlu_pro/mmlu_pro_adapter.py +80 -99
  108. evalscope/benchmarks/mmlu_redux/mmlu_redux_adapter.py +64 -110
  109. evalscope/benchmarks/mmmu/__init__.py +0 -0
  110. evalscope/benchmarks/mmmu/mmmu_adapter.py +159 -0
  111. evalscope/benchmarks/mmmu_pro/__init__.py +0 -0
  112. evalscope/benchmarks/mmmu_pro/mmmu_pro_adapter.py +129 -0
  113. evalscope/benchmarks/musr/musr_adapter.py +33 -64
  114. evalscope/benchmarks/needle_haystack/needle_haystack_adapter.py +196 -152
  115. evalscope/benchmarks/process_bench/process_bench_adapter.py +144 -76
  116. evalscope/benchmarks/race/race_adapter.py +33 -119
  117. evalscope/benchmarks/simple_qa/simple_qa_adapter.py +72 -70
  118. evalscope/benchmarks/super_gpqa/{five_shot_prompt.txt → prompt.py} +14 -16
  119. evalscope/benchmarks/super_gpqa/super_gpqa_adapter.py +73 -117
  120. evalscope/benchmarks/super_gpqa/utils.py +2 -1
  121. evalscope/benchmarks/tau_bench/generation.py +147 -0
  122. evalscope/benchmarks/tau_bench/tau_bench_adapter.py +114 -60
  123. evalscope/benchmarks/text2image/__init__.py +0 -0
  124. evalscope/benchmarks/text2image/evalmuse_adapter.py +78 -0
  125. evalscope/benchmarks/text2image/genai_bench_adapter.py +53 -0
  126. evalscope/benchmarks/text2image/general_t2i_adapter.py +42 -0
  127. evalscope/benchmarks/text2image/hpdv2_adapter.py +52 -0
  128. evalscope/benchmarks/text2image/tifa_adapter.py +27 -0
  129. evalscope/benchmarks/tool_bench/tool_bench_adapter.py +91 -70
  130. evalscope/benchmarks/trivia_qa/trivia_qa_adapter.py +56 -124
  131. evalscope/benchmarks/truthful_qa/truthful_qa_adapter.py +70 -266
  132. evalscope/benchmarks/winogrande/winogrande_adapter.py +28 -54
  133. evalscope/cli/cli.py +2 -0
  134. evalscope/cli/start_app.py +7 -1
  135. evalscope/cli/start_perf.py +7 -1
  136. evalscope/cli/start_server.py +6 -3
  137. evalscope/collections/__init__.py +2 -10
  138. evalscope/collections/sampler.py +10 -10
  139. evalscope/collections/schema.py +13 -11
  140. evalscope/config.py +157 -57
  141. evalscope/constants.py +37 -61
  142. evalscope/evaluator/__init__.py +1 -1
  143. evalscope/evaluator/evaluator.py +275 -419
  144. evalscope/filters/__init__.py +2 -0
  145. evalscope/filters/extraction.py +126 -0
  146. evalscope/filters/selection.py +57 -0
  147. evalscope/metrics/__init__.py +13 -13
  148. evalscope/metrics/llm_judge.py +47 -33
  149. evalscope/metrics/math_parser.py +27 -22
  150. evalscope/metrics/metric.py +307 -0
  151. evalscope/metrics/metrics.py +22 -18
  152. evalscope/metrics/t2v_metrics/__init__.py +0 -52
  153. evalscope/metrics/t2v_metrics/models/clipscore_models/build_mps_model/clip_model.py +4 -2
  154. evalscope/metrics/t2v_metrics/models/clipscore_models/build_mps_model/cross_modeling.py +9 -13
  155. evalscope/metrics/t2v_metrics/models/clipscore_models/clip_model.py +2 -1
  156. evalscope/metrics/t2v_metrics/models/clipscore_models/hpsv2_model.py +3 -2
  157. evalscope/metrics/t2v_metrics/models/clipscore_models/mps_model.py +2 -1
  158. evalscope/metrics/t2v_metrics/models/clipscore_models/pickscore_model.py +2 -2
  159. evalscope/metrics/t2v_metrics/models/itmscore_models/blip2_itm_model.py +2 -1
  160. evalscope/metrics/t2v_metrics/models/itmscore_models/fga_blip2_model.py +4 -2
  161. evalscope/metrics/t2v_metrics/models/itmscore_models/image_reward/ImageReward.py +10 -5
  162. evalscope/metrics/t2v_metrics/models/itmscore_models/image_reward/blip_pretrain.py +4 -2
  163. evalscope/metrics/t2v_metrics/models/itmscore_models/image_reward_model.py +2 -1
  164. evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5/model/language_model/clip_t5.py +15 -9
  165. evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5/model/multimodal_encoder/clip_encoder.py +4 -2
  166. evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5_model.py +15 -10
  167. evalscope/metrics/t2v_metrics/models/vqascore_models/gpt4v_model.py +9 -6
  168. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/config.py +2 -2
  169. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/gradcam.py +4 -2
  170. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/logger.py +4 -2
  171. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/optims.py +3 -9
  172. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/registry.py +16 -10
  173. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/vqa_tools/vqa.py +3 -2
  174. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/vqa_tools/vqa_eval.py +4 -2
  175. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/__init__.py +8 -4
  176. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/Qformer.py +47 -25
  177. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2_qformer.py +12 -7
  178. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2_t5.py +23 -17
  179. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2_t5_instruct.py +33 -23
  180. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/fga_blip2.py +2 -1
  181. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/modeling_llama.py +46 -30
  182. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/modeling_t5.py +69 -37
  183. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/__init__.py +7 -5
  184. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip.py +6 -4
  185. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_image_text_matching.py +7 -5
  186. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_nlvr.py +3 -2
  187. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_outputs.py +5 -2
  188. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_vqa.py +17 -13
  189. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/nlvr_encoder.py +35 -19
  190. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/clip_vit.py +14 -12
  191. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/eva_vit.py +63 -52
  192. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/med.py +63 -38
  193. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/vit.py +6 -3
  194. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/processors/__init__.py +6 -2
  195. evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/processors/randaugment.py +3 -2
  196. evalscope/metrics/t2v_metrics/models/vqascore_models/mm_utils.py +15 -13
  197. evalscope/metrics/t2v_metrics/models/vqascore_models/vqa_model.py +3 -2
  198. evalscope/models/__init__.py +6 -29
  199. evalscope/models/image_edit_model.py +125 -0
  200. evalscope/models/mockllm.py +65 -0
  201. evalscope/models/model_apis.py +67 -0
  202. evalscope/models/modelscope.py +455 -0
  203. evalscope/models/openai_compatible.py +126 -0
  204. evalscope/models/text2image_model.py +124 -0
  205. evalscope/models/utils/openai.py +701 -0
  206. evalscope/perf/benchmark.py +4 -1
  207. evalscope/perf/http_client.py +4 -2
  208. evalscope/perf/plugin/api/custom_api.py +5 -4
  209. evalscope/perf/plugin/api/openai_api.py +11 -9
  210. evalscope/perf/plugin/datasets/custom.py +2 -1
  211. evalscope/perf/plugin/datasets/flickr8k.py +1 -1
  212. evalscope/perf/plugin/datasets/kontext_bench.py +1 -1
  213. evalscope/perf/plugin/datasets/line_by_line.py +2 -1
  214. evalscope/perf/plugin/datasets/longalpaca.py +2 -1
  215. evalscope/perf/plugin/datasets/openqa.py +4 -2
  216. evalscope/perf/utils/benchmark_util.py +15 -10
  217. evalscope/perf/utils/db_util.py +9 -6
  218. evalscope/perf/utils/local_server.py +11 -3
  219. evalscope/perf/utils/rich_display.py +16 -10
  220. evalscope/report/__init__.py +2 -3
  221. evalscope/report/combinator.py +18 -12
  222. evalscope/report/generator.py +51 -35
  223. evalscope/report/{utils.py → report.py} +8 -6
  224. evalscope/run.py +33 -47
  225. evalscope/summarizer.py +1 -1
  226. evalscope/third_party/toolbench_static/llm/swift_infer.py +0 -4
  227. evalscope/utils/__init__.py +21 -2
  228. evalscope/utils/chat_service.py +3 -2
  229. evalscope/utils/deprecation_utils.py +12 -1
  230. evalscope/utils/function_utils.py +29 -0
  231. evalscope/utils/import_utils.py +23 -1
  232. evalscope/utils/io_utils.py +142 -6
  233. evalscope/utils/json_schema.py +208 -0
  234. evalscope/utils/logger.py +51 -12
  235. evalscope/utils/model_utils.py +11 -7
  236. evalscope/utils/multi_choices.py +288 -0
  237. evalscope/utils/url_utils.py +65 -0
  238. evalscope/version.py +2 -2
  239. {evalscope-0.17.1.dist-info → evalscope-1.0.1.dist-info}/METADATA +108 -62
  240. {evalscope-0.17.1.dist-info → evalscope-1.0.1.dist-info}/RECORD +258 -226
  241. tests/benchmark/test_eval.py +385 -0
  242. tests/benchmark/test_image_edit.py +65 -0
  243. tests/{aigc → benchmark}/test_t2i.py +22 -4
  244. tests/benchmark/test_vlm.py +80 -0
  245. tests/cli/test_all.py +85 -47
  246. tests/cli/test_collection.py +20 -8
  247. tests/cli/test_custom.py +22 -15
  248. tests/cli/test_reasoning.py +81 -0
  249. tests/common.py +73 -0
  250. tests/perf/test_perf.py +4 -2
  251. tests/rag/test_clip_benchmark.py +0 -2
  252. evalscope/benchmarks/aigc/t2i/base.py +0 -56
  253. evalscope/benchmarks/aigc/t2i/evalmuse_adapter.py +0 -78
  254. evalscope/benchmarks/aigc/t2i/genai_bench_adapter.py +0 -58
  255. evalscope/benchmarks/aigc/t2i/general_t2i_adapter.py +0 -58
  256. evalscope/benchmarks/aigc/t2i/hpdv2_adapter.py +0 -57
  257. evalscope/benchmarks/aigc/t2i/tifa_adapter.py +0 -37
  258. evalscope/benchmarks/arc/ai2_arc.py +0 -151
  259. evalscope/benchmarks/benchmark.py +0 -81
  260. evalscope/benchmarks/ceval/ceval_exam.py +0 -146
  261. evalscope/benchmarks/cmmlu/cmmlu.py +0 -161
  262. evalscope/benchmarks/cmmlu/samples.jsonl +0 -5
  263. evalscope/benchmarks/competition_math/competition_math.py +0 -79
  264. evalscope/benchmarks/data_adapter.py +0 -528
  265. evalscope/benchmarks/filters.py +0 -59
  266. evalscope/benchmarks/gsm8k/gsm8k.py +0 -121
  267. evalscope/benchmarks/hellaswag/hellaswag.py +0 -112
  268. evalscope/benchmarks/humaneval/humaneval.py +0 -79
  269. evalscope/benchmarks/mmlu/mmlu.py +0 -160
  270. evalscope/benchmarks/mmlu/samples.jsonl +0 -5
  271. evalscope/benchmarks/process_bench/critique_template.txt +0 -13
  272. evalscope/benchmarks/race/race.py +0 -104
  273. evalscope/benchmarks/race/samples.jsonl +0 -5
  274. evalscope/benchmarks/super_gpqa/zero_shot_prompt.txt +0 -4
  275. evalscope/benchmarks/trivia_qa/trivia_qa.py +0 -89
  276. evalscope/benchmarks/truthful_qa/truthful_qa.py +0 -163
  277. evalscope/benchmarks/utils.py +0 -60
  278. evalscope/collections/evaluator.py +0 -375
  279. evalscope/metrics/completion_parsers.py +0 -227
  280. evalscope/metrics/named_metrics.py +0 -55
  281. evalscope/models/adapters/__init__.py +0 -14
  282. evalscope/models/adapters/base_adapter.py +0 -84
  283. evalscope/models/adapters/bfcl_adapter.py +0 -246
  284. evalscope/models/adapters/chat_adapter.py +0 -207
  285. evalscope/models/adapters/choice_adapter.py +0 -222
  286. evalscope/models/adapters/custom_adapter.py +0 -71
  287. evalscope/models/adapters/server_adapter.py +0 -236
  288. evalscope/models/adapters/t2i_adapter.py +0 -79
  289. evalscope/models/adapters/tau_bench_adapter.py +0 -189
  290. evalscope/models/custom/__init__.py +0 -4
  291. evalscope/models/custom/custom_model.py +0 -50
  292. evalscope/models/custom/dummy_model.py +0 -99
  293. evalscope/models/local_model.py +0 -128
  294. evalscope/models/register.py +0 -41
  295. tests/cli/test_run.py +0 -489
  296. /evalscope/{benchmarks/aigc → api}/__init__.py +0 -0
  297. /evalscope/benchmarks/{aigc/t2i → image_edit}/__init__.py +0 -0
  298. {evalscope-0.17.1.dist-info → evalscope-1.0.1.dist-info}/LICENSE +0 -0
  299. {evalscope-0.17.1.dist-info → evalscope-1.0.1.dist-info}/WHEEL +0 -0
  300. {evalscope-0.17.1.dist-info → evalscope-1.0.1.dist-info}/entry_points.txt +0 -0
  301. {evalscope-0.17.1.dist-info → evalscope-1.0.1.dist-info}/top_level.txt +0 -0
  302. /tests/{aigc → benchmark}/__init__.py +0 -0
evalscope/__init__.py CHANGED
@@ -1,5 +1,8 @@
1
1
  # Copyright (c) Alibaba, Inc. and its affiliates.
2
-
2
+ from evalscope.benchmarks import * # registered benchmarks
3
3
  from evalscope.config import TaskConfig
4
+ from evalscope.filters import extraction, selection # registered filters
5
+ from evalscope.metrics import metric # registered metrics
6
+ from evalscope.models import model_apis # need for register model apis
4
7
  from evalscope.run import run_task
5
8
  from .version import __release_datetime__, __version__
evalscope/api/benchmark/__init__.py ADDED
@@ -0,0 +1,3 @@
1
+ from .adapters import DefaultDataAdapter, ImageEditAdapter, MultiChoiceAdapter, Text2ImageAdapter, VisionLanguageAdapter
2
+ from .benchmark import DataAdapter
3
+ from .meta import BenchmarkMeta
evalscope/api/benchmark/adapters/__init__.py ADDED
@@ -0,0 +1,5 @@
1
+ from .default_data_adapter import DefaultDataAdapter
2
+ from .image_edit_adapter import ImageEditAdapter
3
+ from .multi_choice_adapter import MultiChoiceAdapter
4
+ from .text2image_adapter import Text2ImageAdapter
5
+ from .vision_language_adapter import VisionLanguageAdapter