evalscope 0.10.0__py3-none-any.whl → 1.2.0__py3-none-any.whl

evalscope-0.10.0.dist-info/RECORD

@@ -1,286 +0,0 @@
-evalscope/__init__.py,sha256=XZYDn3ShhM_48je5qQgwymtSdpTt8zYEnNfanYnpBdA,181
-evalscope/arguments.py,sha256=v6IyhjgBACDkapnZYi6DeBI1aZxRVA-mx7KR1j72lYs,4493
-evalscope/config.py,sha256=4klkNziKT4r8a4Z1imkiY16-S8iER1BYPMOG4nJg9lU,8571
-evalscope/constants.py,sha256=bkcDVbB4Pr1Qxz83qefcWjEetVGiHTcx3m84WX14ASI,3330
-evalscope/run.py,sha256=KKZBy2hr8_BscE0ZR1rN9U7iPc1eZYeeInfXe3EY7lA,5718
-evalscope/run_arena.py,sha256=WXPCT0L-b_KvLBQ9KnrVW6y8icdDcqVhaXjTZMpS8k8,8572
-evalscope/summarizer.py,sha256=Wnt8Y61PasOkigo8zMpi1qdFzfETjfnDtCDDQ6VwgDw,5867
-evalscope/version.py,sha256=59oai-Z2lJog2HCNhMbBxRg4D3vkwPK5sfffmDSPntE,119
-evalscope/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/backend/base.py,sha256=qYu8Shokrtrx-N6T_BAJk_6OCpovUBYuN0p3wngt-dw,1030
-evalscope/backend/opencompass/__init__.py,sha256=UP_TW5KBq6V_Nvqkeb7PGvGGX3rVYussT43npwCwDgE,135
-evalscope/backend/opencompass/api_meta_template.py,sha256=DaBJg15ZSIjxroXiygl3-4RdmIe_FD7xHbXvjSZmkQA,1706
-evalscope/backend/opencompass/backend_manager.py,sha256=y5NnAIY1pI7E1ZSeKU3acrD-oyH3uMGL7M3nPp1WiHU,10381
-evalscope/backend/opencompass/tasks/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/backend/opencompass/tasks/eval_api.py,sha256=ZaGdUbEOtAW5VX3ZXmpHIttg_QrID34EnBTylD3uvos,1152
-evalscope/backend/opencompass/tasks/eval_datasets.py,sha256=JHSq4EnPJgv4sRJJplLH80EqE3ghtkn2k8HnV6DaDew,5406
-evalscope/backend/rag_eval/__init__.py,sha256=jFWj8l8bPAu1sz7wtX5gGIweBFC8c2LzXUPz7tGambE,284
-evalscope/backend/rag_eval/backend_manager.py,sha256=Cw322R1j-L8vMERAWEXUTT-0a1K-V6KhQOtrOhgKVMM,2857
-evalscope/backend/rag_eval/clip_benchmark/__init__.py,sha256=C8Vetf52nyHiRwY2Pm74Bjn3UpWboQeghCGNh67X1EM,151
-evalscope/backend/rag_eval/clip_benchmark/arguments.py,sha256=d5UkbC3RXb6iyzy_ILumToAVO1AdwvDeyOiX5KB2u0g,1530
-evalscope/backend/rag_eval/clip_benchmark/dataset_builder.py,sha256=anuIhRk9OC8y0LNBjvttSXppc99gbz-f0TYQjnyLLyU,8347
-evalscope/backend/rag_eval/clip_benchmark/task_template.py,sha256=2NQRvlYY2SOzvOOj9WRLyxvRlyj8CAcgbQqgsv-Xjgw,3929
-evalscope/backend/rag_eval/clip_benchmark/tasks/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/backend/rag_eval/clip_benchmark/tasks/image_caption.py,sha256=CQnWZZTQ0FOzDtmGv7OF0W4Cv4g6u4_LQ93koDu1pes,2556
-evalscope/backend/rag_eval/clip_benchmark/tasks/zeroshot_classification.py,sha256=NwpxNECN7NFgtlVdKY7vet5m-gAmIp8MJYka0eexWu0,7424
-evalscope/backend/rag_eval/clip_benchmark/tasks/zeroshot_retrieval.py,sha256=t0Uq7W0sPDBJS1rqp70KgSfeRQ3c7u8YeGhj5Yiu6rk,5646
-evalscope/backend/rag_eval/clip_benchmark/utils/webdataset_convert.py,sha256=rZY-TulG-Cb8b6GTBxqTDYQ_4Ois3kbgKhuunZq8Ato,8407
-evalscope/backend/rag_eval/clip_benchmark/utils/webdatasets.txt,sha256=eiiAaxhS48b5rVLy5O9VvFfV2AfxY86ITu_iqT7ZLkQ,649
-evalscope/backend/rag_eval/cmteb/__init__.py,sha256=I502GHPFYo8BwlFvoljGKI24PY76eBXJQiquWk8nJNU,280
-evalscope/backend/rag_eval/cmteb/arguments.py,sha256=Z3GkGi7zjK85JynG-7CSVPmAxPRcGYuykkgfbxgn7_E,2317
-evalscope/backend/rag_eval/cmteb/base.py,sha256=UCobQ81dHkiTmIz_0BJ_VANj_uG6mkJbYLKJztvMXfo,2849
-evalscope/backend/rag_eval/cmteb/task_template.py,sha256=FyFs1reefcsFCrWyi7Ya5dnFYvBhtxph2wIaFtOtFls,2595
-evalscope/backend/rag_eval/cmteb/tasks/Classification.py,sha256=sqbH0XmSiIm4n5UX5sXMwJHby1r-d35mwW1tKIhb2Hg,10848
-evalscope/backend/rag_eval/cmteb/tasks/Clustering.py,sha256=-GTwORxILSkkXXGtTxuPTKSHNXQEllCRoUjuR7pnwFM,8962
-evalscope/backend/rag_eval/cmteb/tasks/CustomTask.py,sha256=pbZBfjeVAKbjLy4tEk6KUVDv-Rv8HNHYWuNkfqf-Vwk,2025
-evalscope/backend/rag_eval/cmteb/tasks/PairClassification.py,sha256=yISp67pXw4fSrsqTiYmfas6uPyqwE45L1c58Tpydc0E,4075
-evalscope/backend/rag_eval/cmteb/tasks/Reranking.py,sha256=AH7jwJ45WAVxVb60I2DTURVanIAbrlZzk-ey_dHWEO0,5491
-evalscope/backend/rag_eval/cmteb/tasks/Retrieval.py,sha256=ofmmeoieXHmU6O14JKWO9GUpuEEmcWwc78Q7ZJjRDZs,11454
-evalscope/backend/rag_eval/cmteb/tasks/STS.py,sha256=uhGLsQTo5lM3-L2Na3WJGqOLQw3c1WxHDA22ePJPxtU,12285
-evalscope/backend/rag_eval/cmteb/tasks/__init__.py,sha256=PKBNyp45hIa3FYNA1psiwtwfwUcn7s9eNt6r5aUpyyY,1505
-evalscope/backend/rag_eval/ragas/__init__.py,sha256=D0yJkN9SuNGIAL3niZw4BI08Yh3HznsUUewdIAa_-LM,171
-evalscope/backend/rag_eval/ragas/arguments.py,sha256=8SYCV15d25ocdDHRqmGMQzd9zR6gwfOrVSFBe4T-KCo,1806
-evalscope/backend/rag_eval/ragas/task_template.py,sha256=a_3bWfLx0j2zJkWgEWNStO0XXAeUFdnFpeukpoGfxLg,1669
-evalscope/backend/rag_eval/ragas/prompts/persona_prompt.py,sha256=fX9sCci787ViGiL3BhGsykx0bnWfOWWEFueaJKyR8g4,793
-evalscope/backend/rag_eval/ragas/tasks/__init__.py,sha256=hErdWKbvV9aRqOpQTzdFHw1tcYoDbnttmic7GpZzKx8,173
-evalscope/backend/rag_eval/ragas/tasks/build_distribution.py,sha256=vFfemiqtPx22u5pwwZxEQJKYf3B9efYmwbpWDI5hY30,1491
-evalscope/backend/rag_eval/ragas/tasks/build_transform.py,sha256=GtAYqdVOy7BxIGyC4rSZ_UfXagKYzE6eEtXbaOI_g-k,5425
-evalscope/backend/rag_eval/ragas/tasks/testset_generation.py,sha256=B5ZETlQw5XTEDnO-VR5yXjSbbg1eUtjGts7M5msK2ik,5618
-evalscope/backend/rag_eval/ragas/tasks/translate_prompt.py,sha256=aP8U9zjIDl26X_YF82SXLpkxoJ4nUurmdKSEoJ-qsLY,2129
-evalscope/backend/rag_eval/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/backend/rag_eval/utils/clip.py,sha256=GLHhPCac2AH35AvRLvVqePA1gIMAewHTFmCJCDZzvqU,5015
-evalscope/backend/rag_eval/utils/embedding.py,sha256=x9HAEfZSSAnT2Tdbf-9a5UmBVagCr__ay5A2nMCPMpg,6258
-evalscope/backend/rag_eval/utils/llm.py,sha256=IaNgdQBnURAmtpK5UPDqfCNrtV_J3wu0s4JWQqKedHA,2568
-evalscope/backend/rag_eval/utils/tools.py,sha256=FU7tNu-8y8V_o_kArFVTTLM_GzL12KBNeXiwQw5SpJA,1529
-evalscope/backend/vlm_eval_kit/__init__.py,sha256=R-GuBm8dAwvDF73XHaGpPSjlt7Y4tycyy-FJgzLdjeY,84
-evalscope/backend/vlm_eval_kit/backend_manager.py,sha256=ZB0wYzPBPyIM0zjfp5C71GcjAgKxKoWxF7RrhuDQBYM,5931
-evalscope/backend/vlm_eval_kit/custom_dataset.py,sha256=D-8Sr0tZblf-3ZR5T0lOggbgFRuy5wq9Nm02GUpNyAs,1620
-evalscope/benchmarks/__init__.py,sha256=b_SWdV1ZyOqFiwc_9lIjKrIvK1rwnF2cCIF7XN9CN8E,932
-evalscope/benchmarks/benchmark.py,sha256=SFDjyxd4t4KEcLBP82zE_KCJ_wXuv8J3XFzIR4M9fFI,2419
-evalscope/benchmarks/data_adapter.py,sha256=Aaspp5dR1aINXAopm0y7LHeMwJbmYXfy5bNm9DpagRo,12051
-evalscope/benchmarks/arc/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/benchmarks/arc/ai2_arc.py,sha256=WtL4Z_ulcCU2KfptWTjTm75T2I2rVGd9aDBBB76P14w,5697
-evalscope/benchmarks/arc/arc_adapter.py,sha256=TdDB3lazJNdUt2bBo1G7zaOAN6YkKXdcgMui1ygQj3Y,6591
-evalscope/benchmarks/bbh/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/benchmarks/bbh/bbh_adapter.py,sha256=pkgIEr_4QyzngUcs0j4oOscFljGoYZcCAS861Afnt_0,8316
-evalscope/benchmarks/bbh/cot_prompts/boolean_expressions.txt,sha256=xnzlaIRyeGlogG49v8nt4vpJO40J06ev4yc8cv0VSRY,1781
-evalscope/benchmarks/bbh/cot_prompts/causal_judgement.txt,sha256=sfo-2iOeVzB0OGgd7NSQFELTGDTsr2DQ3u-g0ivI-sM,3653
-evalscope/benchmarks/bbh/cot_prompts/date_understanding.txt,sha256=UJBsc3Mwz8TZngdWH_NFlhhNbLhNHK6FvW9FHcS8H5g,1167
-evalscope/benchmarks/bbh/cot_prompts/disambiguation_qa.txt,sha256=N28JGB5_023fBzoo5HImvjz3A0zPZGoiTMPngQY8pNo,3568
-evalscope/benchmarks/bbh/cot_prompts/dyck_languages.txt,sha256=pkUw0ezfvNgbYzUKCchJ6o7bg6UCVL_62LWqS6lKZY0,2405
-evalscope/benchmarks/bbh/cot_prompts/formal_fallacies.txt,sha256=LDRYUp6fGvG6K2l69VvDF5Szf-CUtgPqobWaQ3MHJ7A,4477
-evalscope/benchmarks/bbh/cot_prompts/geometric_shapes.txt,sha256=H4LkGVmx3U4F6vuqRYXKDpHOBCu7MYksLFWp1QfyDPk,4831
-evalscope/benchmarks/bbh/cot_prompts/hyperbaton.txt,sha256=H8BorN-CyUrf0vrIANSgEILynJhpS02CiGjn-qad9NQ,3114
-evalscope/benchmarks/bbh/cot_prompts/logical_deduction_five_objects.txt,sha256=0e-abSxfoGJC8aYYtRCHlK_2UkiFwffSnv4iN7XXPLs,2505
-evalscope/benchmarks/bbh/cot_prompts/logical_deduction_seven_objects.txt,sha256=0e-abSxfoGJC8aYYtRCHlK_2UkiFwffSnv4iN7XXPLs,2505
-evalscope/benchmarks/bbh/cot_prompts/logical_deduction_three_objects.txt,sha256=0e-abSxfoGJC8aYYtRCHlK_2UkiFwffSnv4iN7XXPLs,2505
-evalscope/benchmarks/bbh/cot_prompts/movie_recommendation.txt,sha256=Q4XZmrnTL1r8JCcB0mvJnb3oNUj45qjM-AfNK2ElWOQ,2121
-evalscope/benchmarks/bbh/cot_prompts/multistep_arithmetic_two.txt,sha256=YJ7chn5QrpNm8VHHqG2B7gYwBUt08fyT_qHhcc9KT-Y,2386
-evalscope/benchmarks/bbh/cot_prompts/navigate.txt,sha256=n3Evl10cdk8VeMfZgUdu3knBH64LmLY5d4cQTnGMLuU,2147
-evalscope/benchmarks/bbh/cot_prompts/object_counting.txt,sha256=SMQGqNi8JVCEVWcVVgQDedzKjslZSxHLcP68ECWX-Xc,1418
-evalscope/benchmarks/bbh/cot_prompts/penguins_in_a_table.txt,sha256=MlrdrvrBaUcW7VjWLLdN-O_yfwVFfYWHobGq099Cyhs,2386
-evalscope/benchmarks/bbh/cot_prompts/reasoning_about_colored_objects.txt,sha256=jcL33cVyscRutNM793hWCryMBWQ-JFLip0DGM1UdAUc,2295
-evalscope/benchmarks/bbh/cot_prompts/ruin_names.txt,sha256=StrmTfLxHtvx4QM-zf1V2u8u1VQSxnZrI7Mwiizvjyw,3481
-evalscope/benchmarks/bbh/cot_prompts/salient_translation_error_detection.txt,sha256=fJKB5sYhH0an4Oeqm53RDIu4mExZJVijCvGzje0nLz4,6141
-evalscope/benchmarks/bbh/cot_prompts/snarks.txt,sha256=tvp4IAtaSNv8CKKeRx_G_PTVMICkenBNmMaq10SNXAE,3114
-evalscope/benchmarks/bbh/cot_prompts/sports_understanding.txt,sha256=yRYmj1f0fwY8tiXTj_iiBYz5u4E4n7Sd3r0bJXHjSco,821
-evalscope/benchmarks/bbh/cot_prompts/temporal_sequences.txt,sha256=-qG7hItFjeahSB0EVvcikmLIR08P_fTIC-J38eV2fyk,3023
-evalscope/benchmarks/bbh/cot_prompts/tracking_shuffled_objects_five_objects.txt,sha256=Su_-fICm9LxGpAkQlRbUZKvet_wPqTK-5jQo_VqJxQI,2604
-evalscope/benchmarks/bbh/cot_prompts/tracking_shuffled_objects_seven_objects.txt,sha256=Su_-fICm9LxGpAkQlRbUZKvet_wPqTK-5jQo_VqJxQI,2604
-evalscope/benchmarks/bbh/cot_prompts/tracking_shuffled_objects_three_objects.txt,sha256=Su_-fICm9LxGpAkQlRbUZKvet_wPqTK-5jQo_VqJxQI,2604
-evalscope/benchmarks/bbh/cot_prompts/web_of_lies.txt,sha256=s_x6u5MLeKpuAHZj3GNQqY1I8vWqQIfJasOp9XcM7Ck,2945
-evalscope/benchmarks/bbh/cot_prompts/word_sorting.txt,sha256=qfTZafCzNiz9ULBaDlfy_LISL617NyH5Nc0-nO0K0LE,2164
-evalscope/benchmarks/ceval/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/benchmarks/ceval/ceval_adapter.py,sha256=2PvM5cvviyVNeFGnz-ymYVhEyPoea52OL_dg7dwVzQQ,11429
-evalscope/benchmarks/ceval/ceval_exam.py,sha256=ngOvb6Fymt7iPWIb2fzrUVpqmUT2VBoqh7X_IH8Bcsc,4824
-evalscope/benchmarks/ceval/samples.jsonl,sha256=dyWhGAdt4eq6Amgu2Ykx8RevUJVFtbhGFSTbDAeUgHc,448
-evalscope/benchmarks/cmmlu/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/benchmarks/cmmlu/cmmlu.py,sha256=Y59NIGUFzJEztJbkehZsG4Cz0J_v9Cyju6xazHMYIcA,5022
-evalscope/benchmarks/cmmlu/cmmlu_adapter.py,sha256=O6FIsJDgg4OiHZSafaDq7jZ2gubWumPMhkdVb8WN-D8,10526
-evalscope/benchmarks/cmmlu/samples.jsonl,sha256=FXbyPQSDorKBGSD0lnOzioZmFjG07lIL87FRDRaMPSY,1722
-evalscope/benchmarks/competition_math/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/benchmarks/competition_math/competition_math.py,sha256=Cehyokift7oDKjc8TdmfblZ6mMc39wQWtqqbUi34QLc,2629
-evalscope/benchmarks/competition_math/competition_math_adapter.py,sha256=ns2WPbqkR52rRKo244WoAeAO9VOESEl_sHCPhym2DnM,6768
-evalscope/benchmarks/general_qa/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/benchmarks/general_qa/general_qa_adapter.py,sha256=1MQXl3Wf_Dnzn7_7BSTu7RT6BOfhhiVyAnqECawxyfM,3899
-evalscope/benchmarks/gsm8k/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/benchmarks/gsm8k/gsm8k.py,sha256=ZDN5lfeZyc_pkTDVY0voC_zUExHE1ZoEgEaTvt5hpXg,4233
-evalscope/benchmarks/gsm8k/gsm8k_adapter.py,sha256=9DuNos8xCOVFOUSJ04LAoBRVPbtqgR4XmOVk6r8ADU8,11114
-evalscope/benchmarks/hellaswag/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/benchmarks/hellaswag/hellaswag.py,sha256=5_c9WbaS1LIdvgXzqEcvjAEtKi2V2Yn0YtszPlFqhXI,4610
-evalscope/benchmarks/hellaswag/hellaswag_adapter.py,sha256=p7Nu-1B2mgbjfth1IhkMSWEC0TxOtD6tp_bOWeeRjts,6332
-evalscope/benchmarks/humaneval/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/benchmarks/humaneval/humaneval.py,sha256=2Exsg6u8FEu0buADY2tETJluSM8tWacvX06nykKKLSE,3395
-evalscope/benchmarks/humaneval/humaneval_adapter.py,sha256=mjWkJqeRM1JVlrLXaCz1qscneLhYySZt8cgdXZSmJWY,5215
-evalscope/benchmarks/ifeval/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/ifeval/ifeval_adapter.py,sha256=JwJoXfAiawx9Rey1MsEtwCdo7QMl_wxOjspiWAuJFko,2074
-evalscope/benchmarks/ifeval/instructions.py,sha256=8mV4f9H1vE8tEnbF1k8uVoDjzJL2tt7lCu2JQaqJelw,56247
-evalscope/benchmarks/ifeval/instructions_registry.py,sha256=tVUmhuSwnOidLtI8onOAw_gpJ6bi8FL07GiX19hSuo8,7288
-evalscope/benchmarks/ifeval/instructions_util.py,sha256=vkemXeylJMmgW8LgfQe4cSy2OF-oH_NcSZtzyZDURW4,25780
-evalscope/benchmarks/ifeval/utils.py,sha256=TKrM1m2qDCUauahogItDdICf4mDk0OjasSxgnxjt2KY,4517
-evalscope/benchmarks/iquiz/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/iquiz/iquiz_adapter.py,sha256=gByj-11KGRTQk2wF1UwNACl8i1svBAEDaj-KJm1XEmw,2387
-evalscope/benchmarks/mmlu/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/benchmarks/mmlu/mmlu.py,sha256=sA8AC0bN7iURrSazqkY31s_reNVbDZSUCB-NCTQsVeI,5042
-evalscope/benchmarks/mmlu/mmlu_adapter.py,sha256=-ONQW0EPAPXFPIpH_Y6zRE-t9j5dT7yABgAU8wxIH4M,11829
-evalscope/benchmarks/mmlu/samples.jsonl,sha256=f5Y2vwbEvNtpE7vrl9BHoJzsdceI4vUAo1frexYyX2o,1345
-evalscope/benchmarks/mmlu_pro/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/benchmarks/mmlu_pro/mmlu_pro_adapter.py,sha256=9Mg7AKb2YL7aCilsXNA5_f1JmETfXQd1kOvLkGcKFEA,4372
-evalscope/benchmarks/race/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/benchmarks/race/race.py,sha256=TtFC3opqEA6q8AQIAFQRGx07FjD9z7iW8wmtxeO61nU,3608
-evalscope/benchmarks/race/race_adapter.py,sha256=9uyQLDA9kVKGu0XhwcBoMyxcgUh3jqWXRO5DahRqUpg,6678
-evalscope/benchmarks/race/samples.jsonl,sha256=bhSktBgU6axYQCClRtQ7nN8D1x815AU8xMAIG1oflG0,1243
-evalscope/benchmarks/trivia_qa/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/benchmarks/trivia_qa/samples.jsonl,sha256=1isBD62PGhCiNbzQa-GFrHHL4XLHIkojWfgSvn7ktf8,3445
-evalscope/benchmarks/trivia_qa/trivia_qa.py,sha256=eekxaXppMLb5tCQqNLOw2MaWlYDhI2IicPzRsTHqb5A,3070
-evalscope/benchmarks/trivia_qa/trivia_qa_adapter.py,sha256=e-jrcCvl8fbPzWCOYKq_sbl4XCulsPzAECGtvTPE-rM,5106
-evalscope/benchmarks/truthful_qa/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/benchmarks/truthful_qa/truthful_qa.py,sha256=A4abSL6WMRcXez8flxsHy-0ZFyRg-moq9rTeOA1TalY,6909
-evalscope/benchmarks/truthful_qa/truthful_qa_adapter.py,sha256=tCVO0RTD_S7z1ky7su5z67dnpgbsEtcH5j0vCpfvUV8,12908
-evalscope/cli/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/cli/base.py,sha256=m1DFlF16L0Lyrn0YNuFj8ByGjVJIoI0jKzAoodIXjRk,404
-evalscope/cli/cli.py,sha256=w_dtXljur9s5lmTn6LbbFL_viTPQB1WAEzhYcId09Og,729
-evalscope/cli/start_app.py,sha256=icLwBq5yHVmJ4C9y-sYq_o_rPvCT-oO-F2r7RlegHv0,706
-evalscope/cli/start_eval.py,sha256=2lyD2WSQ0DnP6T31VvTimQ-6POnwxeEP9GLPFnT7Tfo,767
-evalscope/cli/start_perf.py,sha256=lEHJBSpzNsO4KGlWfQc-EfZGXq1M_FpOwtRxRdb4fso,813
-evalscope/cli/start_server.py,sha256=DQRIfbsHaOAsVcLGF6iRyJnxmd5Sf_tgytpJNfiWCeE,3662
-evalscope/collections/__init__.py,sha256=hd68Qf-ryeDsz5Pu-Dh83M5V5RE5mhLsG-vc55n5n0o,228
-evalscope/collections/evaluator.py,sha256=_XaLn_cSKvAW96aNwaaPbrBDPl9qn0VrsTjID_y7SpM,8910
-evalscope/collections/sampler.py,sha256=6Tp0jN7bJQqG-7AQ2UDPDur6O5aC_nl0N-OV9HfuE9Q,4769
-evalscope/collections/schema.py,sha256=Ns47HXt7Ym4sPdPyxStxALHUid2cW7kWhqvw_jK_p-4,4172
-evalscope/evaluator/__init__.py,sha256=S6MU1O_iiNAaKxNIhO9MEmdW-BSNf_YH2l6NQ9lxVNo,103
-evalscope/evaluator/evaluator.py,sha256=0IOuWQ4KgWuMisNmFqh4-id3d1Kkbkf4JW-6hVz7tqU,16638
-evalscope/evaluator/rating_eval.py,sha256=uo0uj9z_TDsxdYlT8WIfNZhFLAfRkW9zn_wlu-F72O0,5575
-evalscope/evaluator/reviewer/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/evaluator/reviewer/auto_reviewer.py,sha256=PDz1Nt_qq0oGZBBwek2-M8VBUNLkOkmYObzR8gO7nEc,16624
-evalscope/metrics/__init__.py,sha256=yzuZjXufrPqVhzNTNaJLJwhs7-Sgb-iNG0I3BdOX7Tg,291
-evalscope/metrics/code_metric.py,sha256=EXE2BZAc9JJT_cpd6eCb0Jo9wwtnzXzHBZxmLzG5Jpw,3300
-evalscope/metrics/math_accuracy.py,sha256=a0L_YT70bsJYn5_POICJyj6ZVFbHek1ly6j_ssV9Xsc,5585
-evalscope/metrics/metrics.py,sha256=H02Hhj9Me2qzUjSzdV57i5Gj6xP_w5kbuPcuPpejlI0,12860
-evalscope/metrics/named_metrics.py,sha256=j-y-d5EJ4FJzOxlIKobKIMUNu--nzAIIc2j0TvDfFb0,574
-evalscope/metrics/rouge_metric.py,sha256=zhIUqenSuxnORR9tamLQBGjFwP91Zei2UiLtcOyseVM,4639
-evalscope/metrics/bundled_rouge_score/__init__.py,sha256=PwbTdk8168FwDJe_l8XIqDuBgZQooDsP31vj7di05Fs,650
-evalscope/metrics/bundled_rouge_score/rouge_scorer.py,sha256=Kq6AObenmLVQ5tN3NgN042a6mgRFQmRO21-ohd9mSa8,11972
-evalscope/metrics/resources/gpt2-zhcn3-v4.bpe,sha256=J_K-oSt9usFEw87Av6j7ETn3J48EsmFuY5_iVvY6xjc,524464
-evalscope/metrics/resources/gpt2-zhcn3-v4.json,sha256=WkM4J_FDPPNQwYi0kj5sM5SVjk2_6bci7tqf8dV9p_U,1289341
-evalscope/models/__init__.py,sha256=pafIEbJq_2DrYjQbgI0SNVxywNYOxvqwk7Dr1P7KEwk,923
-evalscope/models/base_adapter.py,sha256=fT3i8c9jRmz_VBcUYMMmXrlCM6JWcixPdgak5yT6Wkw,2177
-evalscope/models/chat_adapter.py,sha256=P6CE0JqWDsE7afNfU_wicdisHLfc46Rw3rwTA0sEGQQ,5398
-evalscope/models/choice_adapter.py,sha256=Zb-UUFpF2tpMGuGH_wFleMxpSb__-SuN1cMF7yj25aI,7661
-evalscope/models/custom_adapter.py,sha256=uj4kbBCwhrXjvSq9f6HgTJ5yJ9FJpvs1k5-9Ekm9RmA,2272
-evalscope/models/local_model.py,sha256=EBclVq5tqUFNOZebRlNnZSvzwtSun7FsZRf2tx0cMt0,2486
-evalscope/models/model.py,sha256=diu4TE1ZFWdynTxsl4DejTNsLdwjxoyj2nsKR-Y8EZE,7343
-evalscope/models/server_adapter.py,sha256=VGk_nTwkLWO7Ln7lV_KSaIBzlSRZzyIs_bWDeJ_pOho,4469
-evalscope/models/custom/__init__.py,sha256=wb6f_Bi39s5sj-VO7EXRDXB2WhyFb49BUtEMk77ksNQ,102
-evalscope/models/custom/custom_model.py,sha256=rBQLAuPEw_OPUtRSCEmxEfpcA8jPj8bAdsmtKs4ygus,1566
-evalscope/models/custom/dummy_model.py,sha256=ODD6pt9FvZq_a54oYsehBDslRKHOsk9zsC9iAZvi5Yg,2020
-evalscope/perf/__init__.py,sha256=rgSXzxIJ67yB_SLUdl4ljem2-ilB-Gw3640f4KWLO1k,51
-evalscope/perf/arguments.py,sha256=8KiD4u51B_twEaIiI0_kw4Jknk3YG4S6XN-vgvutChA,9233
-evalscope/perf/benchmark.py,sha256=qNgDNseW8N0beuAB_4-JVtTdHs7ZaJEHK5XnkMU9vRU,9618
-evalscope/perf/http_client.py,sha256=TfnQT9OaBlUCpGwi4ifSJBaaGsn3P2KVBPMGuw-Rqkk,7073
-evalscope/perf/main.py,sha256=SUMz8S2XPL8JaSL1-vy8qkrb34d5vp6DfQdwIGOUXTk,1277
-evalscope/perf/plugin/__init__.py,sha256=1sl5s-csrwKb_LVTnpF3HqArz06TRD5LYJ0hpqvokUA,85
-evalscope/perf/plugin/registry.py,sha256=w1IAt6GDdluzSYK5i-yrntvx3_EvIIqJamEL0xZv3zA,1323
-evalscope/perf/plugin/api/__init__.py,sha256=Ckzbq4CkSMVQTedQcDHCYlRd6FTwQAElt2mHB-VXJac,195
-evalscope/perf/plugin/api/base.py,sha256=B_H04qKx7eRTn155rnDrbTYur7PK1mvxfQKYcqYbndU,2118
-evalscope/perf/plugin/api/custom_api.py,sha256=ay1AGi4y2opjwyRl0J0A54-vLB-pBj3QBFkzog0KA-g,3787
-evalscope/perf/plugin/api/dashscope_api.py,sha256=V5fwn-p_fLH0dWKzhN9TvYSHRgla4INfXC4NDaIjoQ8,3825
-evalscope/perf/plugin/api/openai_api.py,sha256=JxQGlzAbM7MBWcr3MvWiAg6E4lqdQLfkk1qK0vUWvn8,6817
-evalscope/perf/plugin/datasets/__init__.py,sha256=9mz2TnVHhxbEKAS9pLbKMQuIoShNlZpGiRo9e2RQLUs,490
-evalscope/perf/plugin/datasets/base.py,sha256=Z-INWueeYjfEZhP4lbTlBMVwIa6BcXZKWx-w7Pop3mA,1786
-evalscope/perf/plugin/datasets/custom.py,sha256=_GSC5yR90_BjcRjdJqrJT2vHQAzskz5XxYOxngUM2Pg,815
-evalscope/perf/plugin/datasets/flickr8k.py,sha256=UzAIFIO0m5inWOkWM1mO6wfV2HOuXAqiTxCJ4b0SiZM,1589
-evalscope/perf/plugin/datasets/line_by_line.py,sha256=IKVZMpKei6XW9DTm9VEssWHE96i1lTqMf0621dA_img,836
-evalscope/perf/plugin/datasets/longalpaca.py,sha256=2aENqCly_DX1dyNcurYsLFJIvXYFph6jWm7z7XETvMk,1176
-evalscope/perf/plugin/datasets/openqa.py,sha256=2pv7yyPSFYTjPhvAGBsHl0eQO8gt7Wk1CaKcfTi3Tnc,1394
-evalscope/perf/plugin/datasets/speed_benchmark.py,sha256=ef8MXhT6756y6LsXSpYeWjmwswu2hRXe2BOVS2_OgVM,1968
-evalscope/perf/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/perf/utils/analysis_result.py,sha256=ig0zPwbUODGh1GUr3GmnNF4lJJp9SQvW0awWiXEIkCI,1212
-evalscope/perf/utils/benchmark_util.py,sha256=T_pXpSCwCNLJgfzgv3IO7kG61ghTLthVMsXZhBCGP_4,5541
-evalscope/perf/utils/db_util.py,sha256=PSBq16uWyzXx0zyoEE4wazWKN19UAA8_GjobS7rTPso,9001
-evalscope/perf/utils/handler.py,sha256=HyKIxbzC0XCyQanlbb7UEY7yaeqjJTePNea8kMV3Sdc,1192
-evalscope/perf/utils/local_server.py,sha256=clF8i0UFmaxBBB6gX05KvVCyzSv0xzsAidz0_sLLlAk,4627
-evalscope/registry/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/registry/config/cfg_arena.yaml,sha256=rub6ceaQxxB1mbSjdoFf0IaVgGfbOonV2nYRebv2OKo,3292
-evalscope/registry/config/cfg_arena_zhihu.yaml,sha256=tvvihBwvoTjoezwTSaZwoGOB44ysofpnin4pNyY9TfQ,2755
-evalscope/registry/config/cfg_pairwise_baseline.yaml,sha256=d05pBiqOk1ejcdd9XE-opZ_ersyttAesF3Iwa2df8O8,3580
-evalscope/registry/config/cfg_single.yaml,sha256=zjsUC3zhU8z7JURaJiz7npkUbFpP82q1ycqUmObC-hc,3056
-evalscope/registry/data/question.jsonl,sha256=WQw5FXvFYerdfwPK1L4YwrWX-TApeAr2X4Zxjznq-oc,12885
-evalscope/registry/data/prompt_template/lmsys_v2.jsonl,sha256=F3PcsoO_UOCztLNmGDYd90K4z4eVufBWz5prKrcqHG0,10554
-evalscope/registry/data/prompt_template/prompt_templates.jsonl,sha256=F3PcsoO_UOCztLNmGDYd90K4z4eVufBWz5prKrcqHG0,10554
-evalscope/registry/data/qa_browser/battle.jsonl,sha256=2MXcYoMItBmttQxSMh2Oa0x51xxqJaWEgSuERUx1O_0,1185590
-evalscope/registry/data/qa_browser/category_mapping.yaml,sha256=3r9nUIciW9205qbtOQF7aI_etM191cM3vlWU8ueG2Co,484
-evalscope/registry/tasks/arc.yaml,sha256=MghUuCmZPEwGqwYhA8ClRWHiSwC3kbHcKMRicQl9aqc,765
-evalscope/registry/tasks/bbh.yaml,sha256=GE3PpE8zw_SROj41LZ5bTm6ZXXZjYOorAdwBCTEePXM,604
-evalscope/registry/tasks/bbh_mini.yaml,sha256=8o9ZiWaCTkN2uTwiOhjBQuyKm7GUw6ZfUZxb2bkOmvs,678
-evalscope/registry/tasks/ceval.yaml,sha256=XDaszb7DROKk8nQDiklirTvDJwkOUJtIN_tcUFVvIJk,703
-evalscope/registry/tasks/ceval_mini.yaml,sha256=4aYW4c0IzgAXSs5dp4d8dJ0OHVp5sD4uiRjChjL1zZg,672
-evalscope/registry/tasks/cmmlu.yaml,sha256=yOgKl1jmfcAfTuUcIMmG5SQhkrbEHEyyP3YuCuIN3l0,703
-evalscope/registry/tasks/eval_qwen-7b-chat_v100.yaml,sha256=egdiM5oG7RSs0M-g8QNikwhJ9tZVgw5FiLy-rIYYHAA,737
-evalscope/registry/tasks/general_qa.yaml,sha256=S3kdlrazWX2VAX2PMhNtBnFZVSnUKBNiAhGEdUqL-8c,702
-evalscope/registry/tasks/gsm8k.yaml,sha256=M2I7otwOSy0usD8yG8d6QziASQlKdhKLflRHMG0LXiM,729
-evalscope/registry/tasks/mmlu.yaml,sha256=cJcMH1Cvgo9PlYoTmeGx2bcZayysltaa6ehK57dDkvo,726
-evalscope/registry/tasks/mmlu_mini.yaml,sha256=K8ouHh7ve5ZsbkqRtV3Jl-DF01YFPuObfwEdACJA4Pk,778
-evalscope/report/__init__.py,sha256=0Wes3ot2hy9s-WwZaBztst8qkNrXkOF-Hwa1WW1e8lY,260
-evalscope/report/app.py,sha256=rqjKgo7BFow4cA-vN9GaihQCd2m55ndHgUkWVr4Koyk,19470
-evalscope/report/combinator.py,sha256=bi6nvTbMrzraZ8kUZ6mIMikk8-qEIVYUhdaH4RE1Tg8,2653
-evalscope/report/generator.py,sha256=2DULY9W8QCUxdtyfNjo8XAP_YxI1LgR95jknK__kYPU,3600
-evalscope/report/utils.py,sha256=DRlbjbqHEmM8rGlA4pwtlHFhOZtyUzcqiS-mejfIDkU,4584
-evalscope/third_party/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/third_party/longbench_write/README.md,sha256=1yLKeSVIcihpoc4KXr8NpK86JbcLssCPx76aOKdPbYI,5431
-evalscope/third_party/longbench_write/__init__.py,sha256=GNbBDc7HAh_V2Hfy5HhND_u7z6OI79czoBlP8lX4PVo,126
-evalscope/third_party/longbench_write/default_task.json,sha256=d_NPShtW10Mc02U3pAuxX9hXd09tZw7QJAr1SvrECcM,694
-evalscope/third_party/longbench_write/default_task.yaml,sha256=YjU8EeyH9UtM8e7_fhrwJNChQdszOAcrKmOi--Awvhk,578
-evalscope/third_party/longbench_write/eval.py,sha256=39McZSDHL7bA5Dg-BSyZ4EiAF1nfTiYJAnx5FqbNYok,11265
-evalscope/third_party/longbench_write/infer.py,sha256=bFsOp--8Qn6qQ-NpdLY0bennQGQl5TMGEngvGda8k7g,4937
-evalscope/third_party/longbench_write/longbench_write.py,sha256=nIR1toB1hvUXR7Lrs3xcY9wqaI-bjeADg_Oscf3HdaY,3991
-evalscope/third_party/longbench_write/utils.py,sha256=nd-YslsOyNGAuyBfAWb2pnTMaGLMQ58lbnJJdrCndeI,815
-evalscope/third_party/longbench_write/resources/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/third_party/longbench_write/resources/judge.txt,sha256=Go1ISY4bUBmEDXXY_DItjAmskuHSaRj5WTNMNH98FSk,1885
-evalscope/third_party/longbench_write/resources/longbench_write.jsonl,sha256=H26ZSXzCTWWJTWXgFAYvOYupRuvdJUt_izOeSNOrV3k,54155
-evalscope/third_party/longbench_write/resources/longbench_write_en.jsonl,sha256=h4AJJ3YfNA5IiZ5N9dR_tyEa1JNqY0INv6l5ZgQUJZ8,24235
-evalscope/third_party/longbench_write/resources/longwrite_ruler.jsonl,sha256=odTr8N8PoWAFZ2kdEcmlLeMDfEo3KXDtLo9S8oieCmI,5718
-evalscope/third_party/longbench_write/tools/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/third_party/longbench_write/tools/data_etl.py,sha256=T7a-4PwZg5alZQh-oTi1zjMxjGmVVZYVwSR9-diZlF8,5971
-evalscope/third_party/longbench_write/tools/openai_api.py,sha256=PiIvvDYJkn041SJkLoroXwl1B8TtwpB7licVfqNSeuQ,8168
-evalscope/third_party/toolbench_static/README.md,sha256=Osdnt0_K-setbmYwDPCPRp2LXxamGp2mE8KsOByPPOY,3944
-evalscope/third_party/toolbench_static/__init__.py,sha256=BO936RxwodHr4OEpV6W3S_keC91OfOd41_msIJ2d0fs,128
-evalscope/third_party/toolbench_static/config_default.json,sha256=KrUzeHL2DNiM5FwY7cH3KZlxTwELCQZ6e39nilfUi0M,368
-evalscope/third_party/toolbench_static/config_default.yaml,sha256=-6n6Zyg9eHN2eexlehSi9LI4F3EPk-3JacrAb6ZoyxI,451
-evalscope/third_party/toolbench_static/eval.py,sha256=do_-lVi_vEoljeLYvt3b_AYSMqpdKzgYnTek9WLSKe8,8236
-evalscope/third_party/toolbench_static/infer.py,sha256=rsADLhEd2IBcC6EI9aD7hSJmo6Oo5b22mnHWBCZLDPs,9010
-evalscope/third_party/toolbench_static/requirements.txt,sha256=OW91Z8hfzh7yQUYgP1Di_E6DgNgGoGP1UcvnqrdCR68,22
-evalscope/third_party/toolbench_static/toolbench_static.py,sha256=ABb9Gy09zMt30tY50AZGxSZ46k3NVEsvuDj6xlLOjeA,1966
-evalscope/third_party/toolbench_static/llm/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/third_party/toolbench_static/llm/swift_infer.py,sha256=usmVelh0ogBlCtSUL0dqp89w2mAqH1Ptv9MURVoGrc8,1209
-evalscope/utils/__init__.py,sha256=jLVoGryuqUh4Km9QWWQBzpqkcVNRK0MbwNaSgckqdiU,139
-evalscope/utils/arena_utils.py,sha256=Gf8VpH4C_oF2Abif_QeL0rAP6tvTzsc0gglpdNkUE48,7155
-evalscope/utils/chat_service.py,sha256=Kh3hEUW_HF158a0QqHbWepHIHRQFJgUM-jCDAcQ_maw,8674
-evalscope/utils/completion_parsers.py,sha256=YWHkLkSfURTcUjNNlCL6PPDICd4F2Ns9figgPN4C97c,2933
-evalscope/utils/io_utils.py,sha256=vm6uJBBqx4fc7jsHGbwNQ6Hbx7XYhjT1Q2dQ7aHjDD0,4172
-evalscope/utils/logger.py,sha256=49F2WDi1g_o8aW8Z29wOt9YHE9LDqkHIgb-d8TVybJY,3635
-evalscope/utils/model_utils.py,sha256=PK7pKNY8ovtGZHNRvDpZ-d8zBHMOkxd6fRVkM8VF06I,736
-evalscope/utils/utils.py,sha256=a6a2vDDxqlj7nY8xynkKkWs_ZPXEU2UMwvxp0JEpHjg,9686
-tests/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-tests/test_run_all.py,sha256=YcMTlWoFpvWY8jevWyIf2G_tz8hgDD1cAwSvmyZt96M,429
-tests/cli/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-tests/cli/test_collection.py,sha256=gx3GySIAPNaLUSf3D3Q3V0WZc21BPdNthIbECHQN0TI,3026
-tests/cli/test_run.py,sha256=aywruYPPweMEHaBOynf0G3liKBKMH_H_e4Znq2PcaR4,5821
-tests/perf/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-tests/perf/test_perf.py,sha256=iB8Mg565SfwPsObdAByHYfZNqN71kUtPW7ucmyiOWo8,3025
-tests/rag/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tests/rag/test_clip_benchmark.py,sha256=Ar8Br2CoAFYT2h4zCv_JKMKCGJKbKGYZgNwJ410ZaoU,2597
-tests/rag/test_mteb.py,sha256=t64FXE-ZsOCLiRJrw-dIDIhKd1OXiaglXaeERs0lOh4,4643
-tests/rag/test_ragas.py,sha256=N_mUBIyxdQ1REzjkoI2sBNluKLLmKatLc3VY1o9uPck,3947
-tests/swift/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-tests/swift/test_run_swift_eval.py,sha256=JKG-0BwTxkbg-XeiXxujPqnVIM3f2EFaJ_9a7p_R4dk,5748
-tests/swift/test_run_swift_vlm_eval.py,sha256=C8DftjewnZaerQWfERI70bU3sQLWQ-ejZUQhtYO5e0o,4898
-tests/swift/test_run_swift_vlm_jugde_eval.py,sha256=THZEXUOSqm9rWslwJHmZyh-Ytv5c_QKpgRW5J2s_69E,6017
-tests/vlm/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-tests/vlm/test_vlmeval.py,sha256=nzWXjw49SlxXgDnYS9N5JSFtcUp8xPOW2YNNzupvtt4,1806
-evalscope-0.10.0.dist-info/LICENSE,sha256=K_2M03pN0PxVMyx9IQUKsHGhhDMkw5ryQ02rlMvzj3I,11416
-evalscope-0.10.0.dist-info/METADATA,sha256=BwbHLPw5NELgkYNQ90wn_iUoDyUQfQD2WSHRD5XkYcM,28975
-evalscope-0.10.0.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-evalscope-0.10.0.dist-info/entry_points.txt,sha256=Qr4oTgGhg_K-iUtKwVH6lWUhFHDUiH9trIqydHGTEug,56
-evalscope-0.10.0.dist-info/top_level.txt,sha256=Yv0iprOqZQ4rfUO-AWJp7Ni6m0Twxny1yvZwO-8hUDM,16
-evalscope-0.10.0.dist-info/RECORD,,

tests/__init__.py

@@ -1 +0,0 @@
-# Copyright (c) Alibaba, Inc. and its affiliates.

tests/cli/__init__.py

@@ -1 +0,0 @@
-# Copyright (c) Alibaba, Inc. and its affiliates.

tests/cli/test_collection.py

@@ -1,57 +0,0 @@
-import json
-import unittest
-
-from evalscope.collections import CollectionSchema, DatasetInfo, WeightedSampler
-from evalscope.constants import EvalType
-from evalscope.utils.io_utils import dump_jsonl_data
-from evalscope.utils.utils import test_level_list
-
-
-class TestCollection(unittest.TestCase):
-    @unittest.skipUnless(0 in test_level_list(), 'skip test in current test level')
-    def test_create_collection(self):
-        schema = CollectionSchema(name='math&reasoning', datasets=[
-                    CollectionSchema(name='math', datasets=[
-                        CollectionSchema(name='generation', datasets=[
-                            DatasetInfo(name='gsm8k', weight=1, task_type='math', tags=['en', 'math']),
-                            DatasetInfo(name='competition_math', weight=1, task_type='math', tags=['en', 'math']),
-                        ]),
-                        CollectionSchema(name='multiple_choice', datasets=[
-                            DatasetInfo(name='cmmlu', weight=2, task_type='math', tags=['zh', 'math'], args={'subset_list': ['college_mathematics', 'high_school_mathematics']}),
-                            DatasetInfo(name='ceval', weight=3, task_type='math', tags=['zh', 'math'], args={'subset_list': ['advanced_mathematics', 'high_school_mathematics', 'discrete_mathematics', 'middle_school_mathematics']}),
-                        ]),
-                    ]),
-                    CollectionSchema(name='reasoning', datasets=[
-                        DatasetInfo(name='arc', weight=1, task_type='reasoning', tags=['en', 'reasoning']),
-                        DatasetInfo(name='ceval', weight=1, task_type='reasoning', tags=['zh', 'reasoning'], args={'subset_list': ['logic']}),
-                        DatasetInfo(name='race', weight=1, task_type='reasoning', tags=['en', 'reasoning']),
-                    ]),
-                ])
-        print(schema.to_dict())
-        print(schema.flatten())
-        schema.dump_json('outputs/schema_test.json')
-
-
-    @unittest.skipUnless(0 in test_level_list(), 'skip test in current test level')
-    def test_generate_data(self):
-        schema = CollectionSchema.from_dict(json.load(open('outputs/schema_test.json', 'r')))
-        print(schema.to_dict())
-        mixed_data = WeightedSampler(schema).sample(100)
-        dump_jsonl_data(mixed_data, 'outputs/mixed_data_test.jsonl')
-
-    @unittest.skipUnless(0 in test_level_list(), 'skip test in current test level')
-    def test_evaluate_collection(self):
-        from evalscope import TaskConfig, run_task
-
-        task_cfg = TaskConfig(
-            model='Qwen2.5-7B-Instruct',
-            api_url='http://127.0.0.1:8801/v1/chat/completions',
-            api_key='EMPTY',
-            eval_type=EvalType.SERVICE,
-            datasets=['data_collection'],
-            dataset_args={'data_collection': {
-                'local_path': 'outputs/mixed_data_test.jsonl'
-                # 'local_path': 'outputs/weighted_mixed_data.jsonl'
-            }},
-        )
-        run_task(task_cfg=task_cfg)

tests/cli/test_run.py

@@ -1,165 +0,0 @@
-# Copyright (c) Alibaba, Inc. and its affiliates.
-import os
-import subprocess
-import torch
-import unittest
-
-from evalscope.constants import EvalType
-from evalscope.run import run_task
-from evalscope.utils import is_module_installed, test_level_list
-from evalscope.utils.logger import get_logger
-
-os.environ['LOG_LEVEL'] = 'DEBUG'
-
-logger = get_logger()
-
-
-class TestRun(unittest.TestCase):
-
-    def setUp(self) -> None:
-        logger.info('Init env for evalscope native run UTs ...\n')
-        self._check_env('evalscope')
-
-    def tearDown(self) -> None:
-        pass
-
-    @staticmethod
-    def _check_env(module_name: str):
-        if is_module_installed(module_name):
-            logger.info(f'{module_name} is installed.')
-        else:
-            raise ModuleNotFoundError(f'run: pip install {module_name}')
-
-    @unittest.skipUnless(0 in test_level_list(), 'skip test in current test level')
-    def test_run_simple_eval(self):
-        model = 'qwen/Qwen2-0.5B-Instruct'
-        datasets = 'arc'  # arc ceval
-        limit = 10
-
-        cmd_simple = f'evalscope eval ' \
-                     f'--model {model} ' \
-                     f'--datasets {datasets} ' \
-                     f'--limit {limit}'
-
-        logger.info(f'Start to run command: {cmd_simple}')
-        run_res = subprocess.run(cmd_simple, text=True, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
-
-        assert run_res.returncode == 0, f'Failed to run command: {cmd_simple}'
-        logger.info(f'>>test_run_simple_eval stdout: {run_res.stdout}')
-        logger.error(f'>>test_run_simple_eval stderr: {run_res.stderr}')
-
-    @unittest.skipUnless(0 in test_level_list(), 'skip test in current test level')
-    def test_run_eval_with_args(self):
-        model = 'qwen/Qwen2-0.5B-Instruct'
-        datasets = 'arc'  # arc ceval
-        limit = 5
-        dataset_args = '{"ceval": {"few_shot_num": 0, "few_shot_random": false}}'
-
-        cmd_with_args = f'evalscope eval ' \
-                        f'--model {model} ' \
-                        f'--datasets {datasets} ' \
-                        f'--limit {limit} ' \
-                        f'--generation-config do_sample=false,temperature=0.0 ' \
-                        f"""--dataset-args \'{dataset_args}\' """
-
-        logger.info(f'Start to run command: {cmd_with_args}')
-        run_res = subprocess.run(cmd_with_args, text=True, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
-
-        assert run_res.returncode == 0, f'Failed to run command: {cmd_with_args}'
-        logger.info(f'>>test_run_eval_with_args stdout: {run_res.stdout}')
-        logger.error(f'>>test_run_eval_with_args stderr: {run_res.stderr}')
-
-    @unittest.skipUnless(0 in test_level_list(), 'skip test in current test level')
-    def test_run_task(self):
-        task_cfg = {'model': 'qwen/Qwen2-0.5B-Instruct',
-                    'datasets': [
-                        'mmlu_pro',
-                        # 'bbh',
-                        'hellaswag',
-                        # 'gsm8k',
-                        # 'arc'
-                        # 'race',
-                        # 'truthful_qa',
-                        # 'trivia_qa',
-                        ],
-                    'limit': 20,
-                    'debug': True}
-        run_task(task_cfg=task_cfg)
-
-
-    @unittest.skipUnless(0 in test_level_list(), 'skip test in current test level')
-    def test_run_custom_task(self):
-        from evalscope.config import TaskConfig
-
-        task_cfg = TaskConfig(
-            model='qwen/Qwen2-0.5B-Instruct',
-            datasets=['ceval', 'general_qa'],  # 数据格式，选择题格式固定为 'ceval'
-            dataset_args={
-                'ceval': {
-                    'local_path': 'custom_eval/text/mcq',  # 自定义数据集路径
-                    'subset_list': [
-                        'example'  # 评测数据集名称，上述 *_dev.csv 中的 *
-                    ]
-                },
-                'general_qa': {
-                    'local_path': 'custom_eval/text/qa',  # 自定义数据集路径
-                    'subset_list': [
-                        'example'  # 评测数据集名称，上述 *_dev.csv 中的 *
-                    ]
-                }
-            },
-        )
-        run_task(task_cfg=task_cfg)
-
-    @unittest.skipUnless(0 in test_level_list(), 'skip test in current test level')
-    def test_run_humaneval(self):
-        from evalscope.config import TaskConfig
-
-        task_cfg = TaskConfig(
-            model='qwen/Qwen2-0.5B-Instruct',
-            datasets=['humaneval'],
-            limit=2
-        )
-
-        run_task(task_cfg=task_cfg)
-
-    @unittest.skipUnless(0 in test_level_list(), 'skip test in current test level')
-    def test_run_server_model(self):
-        from evalscope.config import TaskConfig
-
-        task_cfg = TaskConfig(
-            model='Qwen2.5-7B-Instruct',
-            api_url='http://127.0.0.1:8801/v1/chat/completions',
-            api_key='EMPTY',
-            eval_type=EvalType.SERVICE,
-            datasets=[
-                'iquiz',
-                # 'ifeval',
-                # 'mmlu',
-                # 'mmlu_pro',
-                # 'race',
-                # 'trivia_qa',
-                # 'cmmlu',
-                # 'humaneval',
-                # 'competition_math',
-                # 'gsm8k',
-                # 'arc',
-                # 'ceval',
-                # 'bbh',
-                # 'hellaswag',
-            ],
-            dataset_args={
-                'ceval': {
-                    'subset_list': [
-                        'computer_network', 'operating_system', 'computer_architecture', 'college_programming'
-                    ]
-                }
-            },
-            # limit=10
-        )
-
-        run_task(task_cfg=task_cfg)
-
-
-if __name__ == '__main__':
-    unittest.main()

tests/perf/__init__.py

@@ -1 +0,0 @@
-# Copyright (c) Alibaba, Inc. and its affiliates.

tests/perf/test_perf.py

@@ -1,101 +0,0 @@
-# Copyright (c) Alibaba, Inc. and its affiliates.
-import os
-
-os.environ['CUDA_VISIBLE_DEVICES'] = '0'
-import unittest
-
-from evalscope.perf.main import run_perf_benchmark
-from evalscope.utils import test_level_list
-
-
-class TestPerf(unittest.TestCase):
-
-    def setUp(self) -> None:
-        pass
-
-    def tearDown(self) -> None:
-        pass
-
-    @unittest.skipUnless(0 in test_level_list(), 'skip test in current test level')
-    def test_run_perf(self):
-        task_cfg = {
-            'url': 'http://127.0.0.1:8001/v1/chat/completions',
-            'parallel': 1,
-            'model': 'qwen2.5',
-            'number': 15,
-            'api': 'openai',
-            'dataset': 'openqa',
-            # 'stream': True,
-            'debug': True,
-        }
-        run_perf_benchmark(task_cfg)
-
-    @unittest.skipUnless(0 in test_level_list(), 'skip test in current test level')
-    def test_run_perf_stream(self):
-        task_cfg = {
-            'url': 'http://127.0.0.1:8000/v1/chat/completions',
-            'parallel': 1,
-            'model': 'qwen2.5',
-            'number': 15,
-            'api': 'openai',
-            'dataset': 'openqa',
-            'stream': True,
-            'debug': True,
-        }
-        run_perf_benchmark(task_cfg)
-
-    @unittest.skipUnless(0 in test_level_list(), 'skip test in current test level')
-    def test_run_perf_speed_benchmark(self):
-        task_cfg = {
-            'url': 'http://127.0.0.1:8001/v1/completions',
-            'parallel': 1,
-            'model': 'qwen2.5',
-            'api': 'openai',
-            'dataset': 'speed_benchmark',
-            'min_tokens': 2048,
-            'max_tokens': 2048,
-            'debug': True,
-        }
-        run_perf_benchmark(task_cfg)
-
-    @unittest.skipUnless(0 in test_level_list(), 'skip test in current test level')
-    def test_run_perf_local(self):
-        task_cfg = {
-            'parallel': 1,
-            'model': 'Qwen/Qwen2.5-0.5B-Instruct',
-            'number': 5,
-            'api': 'local',
-            'dataset': 'openqa',
-            'debug': True,
-        }
-        run_perf_benchmark(task_cfg)
-
-    @unittest.skipUnless(0 in test_level_list(), 'skip test in current test level')
-    def test_run_perf_local_stream(self):
-        task_cfg = {
-            'parallel': 1,
-            'model': 'Qwen/Qwen2.5-0.5B-Instruct',
-            'number': 5,
-            'api': 'local',
-            'dataset': 'openqa',
-            'stream': True,
-            'debug': True,
-        }
-        run_perf_benchmark(task_cfg)
-
-    @unittest.skipUnless(0 in test_level_list(), 'skip test in current test level')
-    def test_run_perf_local_speed_benchmark(self):
-        task_cfg = {
-            'parallel': 1,
-            'model': 'Qwen/Qwen2.5-0.5B-Instruct',
-            'api': 'local_vllm',
-            'dataset': 'speed_benchmark',
-            'min_tokens': 2048,
-            'max_tokens': 2048,
-            'debug': True,
-        }
-        run_perf_benchmark(task_cfg)
-
-
-if __name__ == '__main__':
-    unittest.main(buffer=False)