evalscope 0.8.0__py3-none-any.whl → 0.8.2__py3-none-any.whl

{evalscope-0.8.0.dist-info → evalscope-0.8.2.dist-info}/RECORD

@@ -1,13 +1,13 @@
 evalscope/__init__.py,sha256=RY0EjssSquqqsysRobElYm9Ix6E41uTXeaeh7lI7kqs,106
 evalscope/arguments.py,sha256=nozBnog45l77jxTFH_lyyJkj04ER3yyIpICepc2tC1Y,3783
-evalscope/config.py,sha256=KYS_O0RdAbruQhqP6mp3rQL0003Oaskx03IroZUGRps,6897
-evalscope/constants.py,sha256=D2MU7bs_qwmcHQ1ge05C5Ekk04XqMyiGxssvKwAecxI,4515
-evalscope/run.py,sha256=5cG81qfdpMN_GtPphvJ7BHboD6LBYHWyodX8ViR1XL4,8874
-evalscope/run_arena.py,sha256=Kmzak4TGdATbOhOCe_zLLRxDvgtkOfs6e4VaxOAzPKk,8550
-evalscope/summarizer.py,sha256=Eq7ZqGKuvrhWVeGriLxHCGupgnJmtvmIGqZYzRNaY8I,6480
-evalscope/version.py,sha256=Xha7v5_YH0Oppyh6iO7HrpSsmv1WCPdQPFtzYTJvG4A,118
+evalscope/config.py,sha256=_4IRpoAssdHEg75UKPKVw6FVaCu2NaP2aOMA5DRsuGU,8444
+evalscope/constants.py,sha256=M5qJ8b7kp-RF52IwBjx5EMjeuiH1e1jdollCsbIT-c4,3753
+evalscope/run.py,sha256=s_qE1ukrt4HBfRVAPJjC1XiqD9k7rSH7lX8yysyf5do,7279
+evalscope/run_arena.py,sha256=6nc_S8KL7B3V4SsnpIexfvczHN9kQwHR9R1GXb2sqgI,8586
+evalscope/summarizer.py,sha256=FgdYz7LlNs5XpDMlj2ULkVQGIg5XVeeWdWJ1_OMweq0,5882
+evalscope/version.py,sha256=uvEbCM3fC0oZ2Rt82Q0oErXsM-iYBNxJtPPLXPwscAU,118
 evalscope/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/backend/base.py,sha256=l7zUHXX2XToIfU_hkVeTSHT9wWURYumyohXCIgywZBI,1021
+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
@@ -42,34 +42,14 @@ evalscope/backend/rag_eval/ragas/__init__.py,sha256=D0yJkN9SuNGIAL3niZw4BI08Yh3H
 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/prompts/chinese/AnswerCorrectness/correctness_prompt_chinese.json,sha256=4wPfjNh-OVFQdvho3CAJ66_B2TZuRZVm6-xUIXokKcY,3935
-evalscope/backend/rag_eval/ragas/prompts/chinese/AnswerCorrectness/long_form_answer_prompt_chinese.json,sha256=wWidnp8726hf6-fY31ZoqCt9zhZgVM260o8MwdBI0d8,1737
-evalscope/backend/rag_eval/ragas/prompts/chinese/AnswerRelevancy/question_generation_chinese.json,sha256=o5RXPz-O1JM8gFRCLCY2iobh0uLc4mznT_zLCpWaPFE,968
-evalscope/backend/rag_eval/ragas/prompts/chinese/ContextPrecision/context_precision_prompt_chinese.json,sha256=eEs6gdAKuYfDohCz9EzM1o0ykIEUbvwoRu1Pd2dL92E,3168
-evalscope/backend/rag_eval/ragas/prompts/chinese/CustomNodeFilter/scoring_prompt_chinese.json,sha256=qZhHR9Ki374Ykb6V8dmptE1whXmPKRvAJ0Gl2akoaX0,216
-evalscope/backend/rag_eval/ragas/prompts/chinese/Faithfulness/nli_statements_message_chinese.json,sha256=k5LjoxcIDM9Yvj0h5bje6ANXEOgFbioRs1i23259Md8,2486
-evalscope/backend/rag_eval/ragas/prompts/chinese/Faithfulness/statement_prompt_chinese.json,sha256=Pn1rGIjfyIeY6BZQEOeR4v-QC5xcmTN6aIh0G2E2Xuo,1740
-evalscope/backend/rag_eval/ragas/prompts/chinese/HeadlinesExtractor/prompt_chinese.json,sha256=p7RrFdNWY1Wo5s03SvtXQSZ-CEn96NkPZ3EHsJ3UIFE,1137
-evalscope/backend/rag_eval/ragas/prompts/chinese/MultiHopAbstractQuerySynthesizer/concept_combination_prompt_chinese.json,sha256=s2mlf9BTWnmnCZ9H3yLZgPvPUPWnPgIIDtRtH0qStMM,991
-evalscope/backend/rag_eval/ragas/prompts/chinese/MultiHopAbstractQuerySynthesizer/generate_query_reference_prompt_chinese.json,sha256=s_6K6surhTGpr5efryHjW-PFDKlYJTTpgXDlC_TbzVw,1943
-evalscope/backend/rag_eval/ragas/prompts/chinese/MultiHopAbstractQuerySynthesizer/theme_persona_matching_prompt_chinese.json,sha256=XmHkc-bj7PFdLxGKoM3UDeOv2FO0X2Pc9Wpd6JOkdns,919
-evalscope/backend/rag_eval/ragas/prompts/chinese/MultiHopSpecificQuerySynthesizer/generate_query_reference_prompt_chinese.json,sha256=p-vCyibNNezGcuID2kGvBDZJGdPXm3NvTTVvH6ij7N4,1973
-evalscope/backend/rag_eval/ragas/prompts/chinese/MultiHopSpecificQuerySynthesizer/theme_persona_matching_prompt_chinese.json,sha256=XmHkc-bj7PFdLxGKoM3UDeOv2FO0X2Pc9Wpd6JOkdns,919
-evalscope/backend/rag_eval/ragas/prompts/chinese/MultiModalFaithfulness/faithfulness_prompt_chinese.json,sha256=yayuzrNO2EO9eIqSv5mthNTVXnw_7D_HOJZ_tse-qw0,1374
-evalscope/backend/rag_eval/ragas/prompts/chinese/MultiModalRelevance/relevance_prompt_chinese.json,sha256=-rOBZuhZGbVrlti3PycavxAoInEry3dMYt9VN3Qvo-E,1475
-evalscope/backend/rag_eval/ragas/prompts/chinese/NERExtractor/prompt_chinese.json,sha256=svZ_xzfQp3KMzdVJoqTVPGnwgls2JjXXplTcUj1jVFo,767
-evalscope/backend/rag_eval/ragas/prompts/chinese/SingleHopSpecificQuerySynthesizer/generate_query_reference_prompt_chinese.json,sha256=VRO9Hy-e5Dba1AkLqxj2R-Ezwoby3BvipM9zNlZJ4GY,1328
-evalscope/backend/rag_eval/ragas/prompts/chinese/SingleHopSpecificQuerySynthesizer/theme_persona_matching_prompt_chinese.json,sha256=XmHkc-bj7PFdLxGKoM3UDeOv2FO0X2Pc9Wpd6JOkdns,919
-evalscope/backend/rag_eval/ragas/prompts/chinese/SummaryExtractor/prompt_chinese.json,sha256=1YVcklCc4otS0mkO0aiNNFx7Zecc1L3wB6ol3NPxTt0,697
-evalscope/backend/rag_eval/ragas/prompts/chinese/ThemesExtractor/prompt_chinese.json,sha256=c70_FGepQm3_dZngdjNudX_iCmu39tvZncyBqNxMrfg,658
 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=WZovQJGyPI33Y-9bUnanR6fIYJzrXgnjD4zVwUJSgCw,5002
-evalscope/backend/rag_eval/utils/embedding.py,sha256=XWI07YeWDALc2etP4DGluYqrid85nKz1tjM91JLZRmM,6252
+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=619eP8pXUcwIBaktBrGNA17j53j9jfg_1JeFDYzMCIE,2582
 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
@@ -122,23 +102,23 @@ evalscope/benchmarks/competition_math/__init__.py,sha256=CDK03RXT-X21WcIAlkrCs0r
 evalscope/benchmarks/competition_math/competition_math.py,sha256=Cehyokift7oDKjc8TdmfblZ6mMc39wQWtqqbUi34QLc,2629
 evalscope/benchmarks/competition_math/competition_math_adapter.py,sha256=cHWJ6LLIWvftFXjGrOidMlZ1RGUFxPgDjs4wmBPSm1Y,18862
 evalscope/benchmarks/general_qa/__init__.py,sha256=N2t-ehNrl9eVAarlSgJvRapm9yOjhfCWhNPPfcUUy-s,409
-evalscope/benchmarks/general_qa/general_qa_adapter.py,sha256=Y7_d6hmh94W2XbzUnDMX9_uKWcarK0zv4Q4mQWUfSZ8,5869
+evalscope/benchmarks/general_qa/general_qa_adapter.py,sha256=cSW0Mq9__-gh-tVoVXD9Rk6h3h2iZW-Fu3RQ16haJhQ,5878
 evalscope/benchmarks/gsm8k/__init__.py,sha256=CtcG_QM8m5zmvMs2N53d7kcm4_hIgsO2qYPyx-71aLw,313
 evalscope/benchmarks/gsm8k/gsm8k.py,sha256=ZDN5lfeZyc_pkTDVY0voC_zUExHE1ZoEgEaTvt5hpXg,4233
-evalscope/benchmarks/gsm8k/gsm8k_adapter.py,sha256=gg65W_pz4mPOBUOwaYIgfUxGKzrmRZRuoEg5xtS8bYg,13830
+evalscope/benchmarks/gsm8k/gsm8k_adapter.py,sha256=KBI9t5F7XW1Cs44QUA7ultkfsXxLyucH9zNYe-jOQQk,13866
 evalscope/benchmarks/hellaswag/__init__.py,sha256=cY1kluaTqC7AvyzwlQYc3BF_kB3LD1gOpg6i7RDr0cI,415
 evalscope/benchmarks/hellaswag/hellaswag.py,sha256=5_c9WbaS1LIdvgXzqEcvjAEtKi2V2Yn0YtszPlFqhXI,4610
-evalscope/benchmarks/hellaswag/hellaswag_adapter.py,sha256=7REJeC8vD8OVtmcqI5TP6cTn88-KOzBs5oOKEZEmESs,8459
+evalscope/benchmarks/hellaswag/hellaswag_adapter.py,sha256=IIesSMPw1Yya4-LjqJt1QVkpOx8RGKwBYTQtmc0VfaQ,8495
 evalscope/benchmarks/humaneval/__init__.py,sha256=lqSlAf1-8Nzhc1j89sj6yAcaLt9pGhqu15M84bmzamc,333
 evalscope/benchmarks/humaneval/humaneval.py,sha256=2Exsg6u8FEu0buADY2tETJluSM8tWacvX06nykKKLSE,3395
-evalscope/benchmarks/humaneval/humaneval_adapter.py,sha256=HxAjkIA-Wt5-wb8kNSDMzZRoHflgsNxIfa1BoeVzwog,1660
+evalscope/benchmarks/humaneval/humaneval_adapter.py,sha256=VAO7siedusq9z3b1J3ztFE4XDopYKqmwe2n-Numg7HY,9149
 evalscope/benchmarks/mmlu/__init__.py,sha256=OGiN1J80WDM72y242o7diYT9Rl-jkVEqTNntCl8Vt4M,385
 evalscope/benchmarks/mmlu/mmlu.py,sha256=sA8AC0bN7iURrSazqkY31s_reNVbDZSUCB-NCTQsVeI,5042
 evalscope/benchmarks/mmlu/mmlu_adapter.py,sha256=8T-fN_Az0gWOyME9nHl3MvcD144TjWknFKcEOMHppAI,15494
 evalscope/benchmarks/mmlu/samples.jsonl,sha256=f5Y2vwbEvNtpE7vrl9BHoJzsdceI4vUAo1frexYyX2o,1345
 evalscope/benchmarks/race/__init__.py,sha256=HVda-CB-Q-N8RbwiVLADXYNY6VLUH-frJ8VCc3jm0Mk,385
 evalscope/benchmarks/race/race.py,sha256=TtFC3opqEA6q8AQIAFQRGx07FjD9z7iW8wmtxeO61nU,3608
-evalscope/benchmarks/race/race_adapter.py,sha256=Ppo7bttx15zB-m-UtguIwIXgqpEKAi_ClIOol0hPQiE,9805
+evalscope/benchmarks/race/race_adapter.py,sha256=WgnWYSctc3VtWm2FAeVDTlxR2hwXsF2tala7n66f5mw,9841
 evalscope/benchmarks/race/samples.jsonl,sha256=bhSktBgU6axYQCClRtQ7nN8D1x815AU8xMAIG1oflG0,1243
 evalscope/benchmarks/trivia_qa/__init__.py,sha256=eLMVC6tfwty5HqrQuGyWeAF2IhRNajWoO1SkLVemQj4,409
 evalscope/benchmarks/trivia_qa/samples.jsonl,sha256=1isBD62PGhCiNbzQa-GFrHHL4XLHIkojWfgSvn7ktf8,3445
@@ -153,12 +133,11 @@ evalscope/cli/cli.py,sha256=yNL3ZeolBc-cVr5D4GByGZWKrmpKIK-48R6wXOXO7Y0,641
 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/evaluator/__init__.py,sha256=h_EyZm7vDqBsGx6CkoQVLg0aMy0tE_IG5uEnheubb0s,174
-evalscope/evaluator/evaluator.py,sha256=MGkuJi9o5Hdbj_fN7qolDqP0B47i9i0ksGd1uc-TMn0,18365
-evalscope/evaluator/humaneval_evaluator.py,sha256=245XRxwulGQpjdapwU8CiYJn1xT0XKxl7hdWvzFxLG0,5964
-evalscope/evaluator/rating_eval.py,sha256=VuDIZcmSlsv1tc8znDGesz8ZwpQ7NvZJPv823Quvht0,5566
+evalscope/evaluator/__init__.py,sha256=S6MU1O_iiNAaKxNIhO9MEmdW-BSNf_YH2l6NQ9lxVNo,103
+evalscope/evaluator/evaluator.py,sha256=wrTWyvyD1eqSvsZRwDRV1UVBxXv7y-2A29UCD9F-5qI,18412
+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=YVTJAHK0uz9hNupsdeTXMM2PISECf8phXq0GYPr4law,16378
+evalscope/evaluator/reviewer/auto_reviewer.py,sha256=nL8k-i92L1iMwjPOnNxzQyZICfukZKJul4ZBvOWkHGw,16414
 evalscope/metrics/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/metrics/code_metric.py,sha256=EXE2BZAc9JJT_cpd6eCb0Jo9wwtnzXzHBZxmLzG5Jpw,3300
 evalscope/metrics/math_accuracy.py,sha256=WqLfACuIeVFrX4q6_c2exnTLn2t10-rjv6sfxcqJJ14,1965
@@ -171,24 +150,24 @@ evalscope/metrics/resources/gpt2-zhcn3-v4.json,sha256=WkM4J_FDPPNQwYi0kj5sM5SVjk
 evalscope/models/__init__.py,sha256=b-jXJ2Cj6dH8notAU7lvCVKbGrcEaf8Gfr5w79qNHAk,111
 evalscope/models/dummy_chat_model.py,sha256=aG3yolnnIN_-gsfF9FsyjyGMewQteEnUfOxTGScROSE,1272
 evalscope/models/model.py,sha256=ZzzVzZHVzuzdt5F1r-rEBT44ZfW9B7R1spsrV-T8nSw,3020
-evalscope/models/model_adapter.py,sha256=XBeSFTR9pXmnhFWRRddcobnITC5T4JKooeFUeWEtUVI,19006
+evalscope/models/model_adapter.py,sha256=5jzDXpFp24ZZ25tjpIMJeDTz-lDSD_EHp040gJOZACc,19007
 evalscope/models/openai_model.py,sha256=-tPBu6v0Ogf_flmG88tFuu66QNKrOyxv3AjYwVtuR44,3313
 evalscope/models/api/__init__.py,sha256=0c75K78O1KaV02BqqtEp-hhtSSClXLawb8E0c2iqN_A,105
 evalscope/models/api/openai_api.py,sha256=PiIvvDYJkn041SJkLoroXwl1B8TtwpB7licVfqNSeuQ,8168
 evalscope/models/custom/__init__.py,sha256=wb6f_Bi39s5sj-VO7EXRDXB2WhyFb49BUtEMk77ksNQ,102
 evalscope/models/custom/custom_model.py,sha256=rBQLAuPEw_OPUtRSCEmxEfpcA8jPj8bAdsmtKs4ygus,1566
 evalscope/perf/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-evalscope/perf/arguments.py,sha256=_gW1tq7SbrAZd05N-FbY_oWrQB0Djs4KUaFdXSfFsr8,9112
-evalscope/perf/benchmark.py,sha256=ff9PFFMY5UucuUihcdo6lSf1X9XXoaOmrpBvjDk5Mrw,9599
+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=-8NsvJZ7uyVfJT9N2lX36KfsHkVTy0r8OcsWPYoKms0,1316
+evalscope/perf/main.py,sha256=Qg99KhGUjnVAMkNofbDsvMGFxijewH8ri3QoW1y1U7U,1292
 evalscope/perf/plugin/__init__.py,sha256=1sl5s-csrwKb_LVTnpF3HqArz06TRD5LYJ0hpqvokUA,85
-evalscope/perf/plugin/registry.py,sha256=PyK3E1AqQFuU4Bs9COvFFCJOaCtmHbfeQOVGtjVYh-I,1304
+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=IplmkCu8v9yQrY5CeqBEQDWdOfOp3vRkiDYUcvhw2yY,3775
 evalscope/perf/plugin/api/dashscope_api.py,sha256=V5fwn-p_fLH0dWKzhN9TvYSHRgla4INfXC4NDaIjoQ8,3825
-evalscope/perf/plugin/api/openai_api.py,sha256=KRN6EjObTG08mcI82kJD3dGK7DoVMUZzrUZ1AgoLEp0,7007
+evalscope/perf/plugin/api/openai_api.py,sha256=WV2EUIl1PTg-Dj7HMSxJrAE7OUxJZqQmZLJZLHffcJo,6805
 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
@@ -199,10 +178,10 @@ evalscope/perf/plugin/datasets/openqa.py,sha256=2pv7yyPSFYTjPhvAGBsHl0eQO8gt7Wk1
 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=xFZSSUoBoFpHRZC69-KS9cK2vqJlL7rIuCEz_MnpnGA,5564
-evalscope/perf/utils/db_util.py,sha256=A2K3otCrNw3K1SMwoYo8a6jekT5nAVvWJepqi31DH28,7479
+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=31EQZ8S_SzgSiBFpc9zRU13GXm2jREvRmPDN5qWKgbg,4468
+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
@@ -229,9 +208,9 @@ evalscope/third_party/longbench_write/README.md,sha256=1yLKeSVIcihpoc4KXr8NpK86J
 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=bZrpaKg9sPXv2VkUxLpfJiNqMIoIj7Pf3eFMqmDncyY,11229
+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=1caNiJvmZL2vwDU6oHUE4cdCViZGYE8yBo9EsMcA-Qw,3955
+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
@@ -239,7 +218,7 @@ evalscope/third_party/longbench_write/resources/longbench_write.jsonl,sha256=H26
 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=nmWKOrD-GeZi0ZGH5jLCGuW3qiLTui8ASSxI2z8l6ls,5962
+evalscope/third_party/longbench_write/tools/data_etl.py,sha256=T7a-4PwZg5alZQh-oTi1zjMxjGmVVZYVwSR9-diZlF8,5971
 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
@@ -247,26 +226,27 @@ evalscope/third_party/toolbench_static/config_default.yaml,sha256=-6n6Zyg9eHN2ee
 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=y4nC9WCBCgBg378aWYAdhmrFte_r_XOkigJs7XJ_iXQ,1930
+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/tools/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-evalscope/tools/combine_reports.py,sha256=1BJ29IEUKoZLM3NAzg_IpU8B9uhljO9-b_hqAYi9RpA,5078
+evalscope/tools/combine_reports.py,sha256=JFf3P_GJLPdlSqpv30D8ioPb7dup3tOTktsELmsKXLI,4900
 evalscope/tools/gen_mmlu_subject_mapping.py,sha256=CUmRdReEU7QfMyprh9I56KmHoRww_zUda_JuyxmCL1A,3277
-evalscope/tools/rewrite_eval_results.py,sha256=2lbDHfF_9abK1tUk2UYZZRwzO68eoiE36dXyh_b-mwg,2011
-evalscope/utils/__init__.py,sha256=hDS1xpoAxtVH4-ZQOXstdg7WYmjcGPQ62Kh54FIgkwU,87
+evalscope/tools/rewrite_eval_results.py,sha256=ODD6pt9FvZq_a54oYsehBDslRKHOsk9zsC9iAZvi5Yg,2020
+evalscope/utils/__init__.py,sha256=ZOri8VHx8LpJBJS90uw8h0Z7gPhtxhjWlBPWuuZgoRE,121
 evalscope/utils/arena_utils.py,sha256=Gf8VpH4C_oF2Abif_QeL0rAP6tvTzsc0gglpdNkUE48,7155
-evalscope/utils/chat_service.py,sha256=N8lJPiVtzdqsHypa42wzb15T7hduXUrRPtU3Atf8yg4,8641
+evalscope/utils/chat_service.py,sha256=VdNPXdFSf-4zxe0Ht74LBcdRNbpb9vzVi86HDEqfXHc,8647
 evalscope/utils/completion_parsers.py,sha256=YWHkLkSfURTcUjNNlCL6PPDICd4F2Ns9figgPN4C97c,2933
-evalscope/utils/logger.py,sha256=IkY0oxkWSvfA0z1m79crioTiqQcnxulNF5HtJNlV0Fc,3174
+evalscope/utils/io_utils.py,sha256=MnEi4llOYtXK81bUQ_XE_WP5qIsVrJ4MlKmWMH9vzFs,3993
+evalscope/utils/logger.py,sha256=4OGlkBsut_wzq-1UcM2DKQKdKs1FRNYGHw538TGvypU,3440
 evalscope/utils/model_utils.py,sha256=zMS1YRu4CzU4CVLZS6e_lgfHIDBqv3YBTJbPF1R2M90,443
-evalscope/utils/utils.py,sha256=PVtpv3WAIm6Bs66Vz4KBDiAiXp8y6Oejxxr1LWHTRsI,15146
+evalscope/utils/utils.py,sha256=lZl5lt4WqjoY5SEfsum8Sc-s_c9GSlmIZlkTAQkMnjE,10485
 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_run.py,sha256=lXR35DDLQjdb-XGA6pKnQC9pJTfTOHjknAN7PEaw8G4,4334
+tests/cli/test_run.py,sha256=pMZvI3b0Vs-UFfciDoPwCYFAaYJzocQjxEaMLFTxYSo,4289
 tests/perf/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
-tests/perf/test_perf.py,sha256=GD5nInXpQG7H1E8wI6dvy4DFSvTEddGDzv-Cu8YV1ts,2995
+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=CaEJ0f1M06Z90c72FQb9z23IC_KZtkURWsc_oRMgQn8,4609
@@ -276,10 +256,10 @@ tests/swift/test_run_swift_eval.py,sha256=JKG-0BwTxkbg-XeiXxujPqnVIM3f2EFaJ_9a7p
 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=21xi0nu4ghDB6_X-Pol7pTfK7aYkAYOp82TQ-MSQv-I,1757
-evalscope-0.8.0.dist-info/LICENSE,sha256=K_2M03pN0PxVMyx9IQUKsHGhhDMkw5ryQ02rlMvzj3I,11416
-evalscope-0.8.0.dist-info/METADATA,sha256=5RKZaNBwuJj84sdAXlNmT11Bm8kGYha6EYnqszwZ1Qk,23190
-evalscope-0.8.0.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-evalscope-0.8.0.dist-info/entry_points.txt,sha256=Qr4oTgGhg_K-iUtKwVH6lWUhFHDUiH9trIqydHGTEug,56
-evalscope-0.8.0.dist-info/top_level.txt,sha256=Yv0iprOqZQ4rfUO-AWJp7Ni6m0Twxny1yvZwO-8hUDM,16
-evalscope-0.8.0.dist-info/RECORD,,
+tests/vlm/test_vlmeval.py,sha256=nzWXjw49SlxXgDnYS9N5JSFtcUp8xPOW2YNNzupvtt4,1806
+evalscope-0.8.2.dist-info/LICENSE,sha256=K_2M03pN0PxVMyx9IQUKsHGhhDMkw5ryQ02rlMvzj3I,11416
+evalscope-0.8.2.dist-info/METADATA,sha256=Fk1p0gh2RycQ7yOBj7fMYym7G-SYj8sL-IZX8cgGxVQ,23709
+evalscope-0.8.2.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+evalscope-0.8.2.dist-info/entry_points.txt,sha256=Qr4oTgGhg_K-iUtKwVH6lWUhFHDUiH9trIqydHGTEug,56
+evalscope-0.8.2.dist-info/top_level.txt,sha256=Yv0iprOqZQ4rfUO-AWJp7Ni6m0Twxny1yvZwO-8hUDM,16
+evalscope-0.8.2.dist-info/RECORD,,

tests/cli/test_run.py

@@ -70,7 +70,7 @@ class TestRun(unittest.TestCase):
 
     @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': ['gsm8k'], 'limit': 2, 'debug': False}
+        task_cfg = {'model': 'qwen/Qwen2-0.5B-Instruct', 'datasets': ['bbh', 'gsm8k', 'arc'], 'limit': 2, 'debug': False}
         run_task(task_cfg=task_cfg)
 
 
@@ -80,33 +80,32 @@ class TestRun(unittest.TestCase):
 
         task_cfg = TaskConfig(
             model='qwen/Qwen2-0.5B-Instruct',
-            datasets=['ceval'],  # 数据格式，选择题格式固定为 'ceval'
+            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_custom_qa(self):
+    def test_run_humaneval(self):
         from evalscope.config import TaskConfig
 
         task_cfg = TaskConfig(
             model='qwen/Qwen2-0.5B-Instruct',
-            datasets=['general_qa'],  # 数据格式，选择题格式固定为 'ceval'
-            dataset_args={
-                '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 *
-                    ]
-                }
-            },
+            datasets=['humaneval'],
+            limit=2
         )
 
         run_task(task_cfg=task_cfg)

tests/perf/test_perf.py

@@ -19,12 +19,13 @@ class TestPerf(unittest.TestCase):
     @unittest.skipUnless(0 in test_level_list(), 'skip test in current test level')
     def test_run_perf(self):
         task_cfg = {
-            'url': 'http://127.0.0.1:8000/v1/chat/completions',
+            '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)
@@ -46,7 +47,7 @@ class TestPerf(unittest.TestCase):
     @unittest.skipUnless(0 in test_level_list(), 'skip test in current test level')
     def test_run_perf_speed_benchmark(self):
         task_cfg = {
-            'url': 'http://127.0.0.1:8000/v1/completions',
+            'url': 'http://127.0.0.1:8001/v1/completions',
             'parallel': 1,
             'model': 'qwen2.5',
             'api': 'openai',

tests/vlm/test_vlmeval.py

@@ -40,8 +40,9 @@ class TestVLMEval(unittest.TestCase):
                 }],  # model name for VLMEval config
                 'nproc': 1,
                 'reuse': True,
-                'work_dir': 'outputs'
-            }
+            },
+            'work_dir': 'outputs',
+            'use_cache': 'outputs/20241216_142838'
         }
 
         logger.info(f'>> Start to run task: {task_cfg}')

evalscope/backend/rag_eval/ragas/prompts/chinese/AnswerCorrectness/correctness_prompt_chinese.json

@@ -1,87 +0,0 @@
-{
-  "ragas_version": "0.2.7",
-  "original_hash": -492257975294377194,
-  "language": "chinese",
-  "instruction": "给定一个真实情况和一个答案陈述，分析每个陈述并将其分类为以下类别之一：TP（真正）：答案中存在的陈述也直接由一个或多个真实情况中的陈述支持，FP（假正）：答案中存在的陈述但没有被任何真实情况中的陈述直接支持，FN（假负）：在真实情况中发现但在答案中不存在的陈述。每个陈述只能属于其中一个类别。为每个分类提供理由。",
-  "examples": [
-    {
-      "input": {
-        "question": "是什么为太阳提供能量，它的主要功能是什么？",
-        "answer": [
-          "太阳的能量来自核裂变，类似于地球上的核反应堆。",
-          "太阳的主要功能是为太阳系提供光。"
-        ],
-        "ground_truth": [
-          "太阳的能量来自核聚变，其中氢原子融合形成氦。",
-          "太阳核心的这种聚变过程释放出巨大的能量。",
-          "来自太阳的能量提供热量和光，这对地球上的生命至关重要。",
-          "太阳的光在地球的气候系统中起着关键作用。",
-          "阳光有助于驱动天气和海洋洋流。"
-        ]
-      },
-      "output": {
-        "TP": [
-          {
-            "statement": "太阳的主要功能是为太阳系提供光。",
-            "reason": "这一说法在某种程度上得到了地面事实的支持，提到太阳提供光和它的作用，尽管它更广泛地关注太阳的能量。"
-          }
-        ],
-        "FP": [
-          {
-            "statement": "太阳的能量来自核裂变，类似于地球上的核反应堆。",
-            "reason": "这一说法是不正确的，与地面事实相矛盾，地面事实指出太阳的能量来自核聚变。"
-          }
-        ],
-        "FN": [
-          {
-            "statement": "太阳的能量来自核聚变，其中氢原子融合形成氦。",
-            "reason": "这种对太阳能量来源的准确描述没有包含在答案中。"
-          },
-          {
-            "statement": "太阳核心的这种聚变过程释放出巨大的能量。",
-            "reason": "这个过程及其重要性没有在答案中提到。"
-          },
-          {
-            "statement": "来自太阳的能量提供热量和光，这对地球上的生命至关重要。",
-            "reason": "答案中只提到了光，忽略了热量及其对生命的必要性，这些在地面事实中都有涵盖。"
-          },
-          {
-            "statement": "太阳的光在地球的气候系统中起着关键作用。",
-            "reason": "太阳光对地球气候系统的这种更广泛的影响没有在答案中提到。"
-          },
-          {
-            "statement": "阳光有助于驱动天气和海洋洋流。",
-            "reason": "答案中省略了阳光对天气模式和海洋洋流的影响。"
-          }
-        ]
-      }
-    },
-    {
-      "input": {
-        "question": "水的沸点是多少？",
-        "answer": [
-          "水的沸点在海平面上是100摄氏度。"
-        ],
-        "ground_truth": [
-          "水的沸点在海平面上是100摄氏度（212华氏度）。",
-          "水的沸点会随着海拔的变化而变化。"
-        ]
-      },
-      "output": {
-        "TP": [
-          {
-            "statement": "水的沸点在海平面上是100摄氏度。",
-            "reason": "这一说法直接得到了地面事实的支持，地面事实具体说明了水的沸点在海平面上是100摄氏度。"
-          }
-        ],
-        "FP": [],
-        "FN": [
-          {
-            "statement": "水的沸点会随着海拔的变化而变化。",
-            "reason": "关于水的沸点如何随海拔变化的额外信息没有在答案中提到。"
-          }
-        ]
-      }
-    }
-  ]
-}

evalscope/backend/rag_eval/ragas/prompts/chinese/AnswerCorrectness/long_form_answer_prompt_chinese.json

@@ -1,36 +0,0 @@
-{
-  "ragas_version": "0.2.7",
-  "original_hash": -8546983388246528139,
-  "language": "chinese",
-  "instruction": "给定一个问题、一个答案和答案中的句子，分析在“句子”下给出的每个句子的复杂性，并将每个句子分解为一个或多个完全可理解的陈述，同时确保每个陈述中不使用代词。将输出格式化为JSON。",
-  "examples": [
-    {
-      "input": {
-        "question": "阿尔伯特·爱因斯坦是谁，他以什么而闻名？",
-        "answer": "他是一位出生于德国的理论物理学家，被广泛认为是有史以来最伟大和最有影响力的物理学家之一。他最著名的是发展了相对论，他还对量子力学理论的发展做出了重要贡献。",
-        "sentences": {
-          "0": "他是一位出生于德国的理论物理学家，被广泛认为是有史以来最伟大和最有影响力的物理学家之一。",
-          "1": "他最著名的是发展了相对论，他还对量子力学理论的发展做出了重要贡献。"
-        }
-      },
-      "output": {
-        "sentences": [
-          {
-            "sentence_index": 0,
-            "simpler_statements": [
-              "阿尔伯特·爱因斯坦是一位出生于德国的理论物理学家。",
-              "阿尔伯特·爱因斯坦被认为是有史以来最伟大和最有影响力的物理学家之一。"
-            ]
-          },
-          {
-            "sentence_index": 1,
-            "simpler_statements": [
-              "阿尔伯特·爱因斯坦最著名的是发展了相对论。",
-              "阿尔伯特·爱因斯坦还对量子力学理论的发展做出了重要贡献。"
-            ]
-          }
-        ]
-      }
-    }
-  ]
-}

evalscope/backend/rag_eval/ragas/prompts/chinese/AnswerRelevancy/question_generation_chinese.json

@@ -1,26 +0,0 @@
-{
-  "ragas_version": "0.2.7",
-  "original_hash": 7951911230338252816,
-  "language": "chinese",
-  "instruction": "为给定的答案生成一个问题，并识别答案是否含糊不清。如果答案含糊不清，则给出1；如果答案明确，则给出0。含糊不清的答案是指那些回避的、模糊的或不明确的答案。例如，“我不知道”或“我不确定”是含糊不清的答案。",
-  "examples": [
-    {
-      "input": {
-        "response": "阿尔伯特·爱因斯坦出生在德国。"
-      },
-      "output": {
-        "question": "阿尔伯特·爱因斯坦出生在哪里？",
-        "noncommittal": 0
-      }
-    },
-    {
-      "input": {
-        "response": "我不知道2023年发明的智能手机的突破性功能，因为我对2022年以后的信息不了解。"
-      },
-      "output": {
-        "question": "2023年发明的智能手机的突破性功能是什么？",
-        "noncommittal": 1
-      }
-    }
-  ]
-}

evalscope/backend/rag_eval/ragas/prompts/chinese/ContextPrecision/context_precision_prompt_chinese.json

@@ -1,41 +0,0 @@
-{
-  "ragas_version": "0.2.7",
-  "original_hash": -5318808809674890018,
-  "language": "chinese",
-  "instruction": "给定问题、答案和背景，验证背景在得出给定答案时是否有用。如果有用，判定为“1”，如果没有用，判定为“0”，并以json格式输出。",
-  "examples": [
-    {
-      "input": {
-        "question": "你能告诉我关于阿尔伯特·爱因斯坦的什么？",
-        "context": "阿尔伯特·爱因斯坦（1879年3月14日－1955年4月18日）是一位德国出生的理论物理学家，被广泛认为是有史以来最伟大和最有影响力的科学家之一。他因发展相对论而闻名，同时也对量子力学做出了重要贡献，因此在20世纪前几十年现代物理学对自然科学理解的革命性重塑中起到了核心作用。他的质能等价公式E=mc²，源于相对论，被称为“世界上最著名的方程”。他因“对理论物理学的贡献，特别是发现光电效应定律”而获得1921年诺贝尔物理学奖，这是量子理论发展的关键一步。他的工作也因其对科学哲学的影响而闻名。在1999年由英国《物理世界》杂志对全球130位顶尖物理学家的调查中，爱因斯坦被评为有史以来最伟大的物理学家。他的智力成就和原创性使爱因斯坦成为天才的代名词。",
-        "answer": "阿尔伯特·爱因斯坦，生于1879年3月14日，是一位德国出生的理论物理学家，被广泛认为是有史以来最伟大和最有影响力的科学家之一。他因对理论物理学的贡献而获得1921年诺贝尔物理学奖。"
-      },
-      "output": {
-        "reason": "提供的背景确实有助于得出给定的答案。背景包括关于阿尔伯特·爱因斯坦的生活和贡献的关键信息，这些信息在答案中得到了反映。",
-        "verdict": 1
-      }
-    },
-    {
-      "input": {
-        "question": "谁赢得了2020年ICC世界杯？",
-        "context": "2022年ICC男子T20世界杯于2022年10月16日至11月13日在澳大利亚举行，是该赛事的第八届。原定于2020年举行，但因COVID-19大流行而推迟。英格兰在决赛中以五个小门击败巴基斯坦，赢得了他们的第二个ICC男子T20世界杯冠军。",
-        "answer": "英格兰"
-      },
-      "output": {
-        "reason": "背景有助于澄清关于2020年ICC世界杯的情况，并指出英格兰是原定于2020年举行但实际上在2022年举行的比赛的获胜者。",
-        "verdict": 1
-      }
-    },
-    {
-      "input": {
-        "question": "世界上最高的山是什么？",
-        "context": "安第斯山脉是世界上最长的大陆山脉，位于南美洲。它横跨七个国家，拥有西半球许多最高的山峰。该山脉以其多样的生态系统而闻名，包括高海拔的安第斯高原和亚马逊雨林。",
-        "answer": "珠穆朗玛峰。"
-      },
-      "output": {
-        "reason": "提供的背景讨论了安第斯山脉，虽然令人印象深刻，但不包括珠穆朗玛峰，也与关于世界最高山的问题没有直接关系。",
-        "verdict": 0
-      }
-    }
-  ]
-}

evalscope/backend/rag_eval/ragas/prompts/chinese/CustomNodeFilter/scoring_prompt_chinese.json

@@ -1,7 +0,0 @@
-{
-  "ragas_version": "0.2.7",
-  "original_hash": -1333942410710431097,
-  "language": "chinese",
-  "instruction": "给定文档摘要和节点内容，将节点内容评分在1到5的范围内。",
-  "examples": []
-}

evalscope/backend/rag_eval/ragas/prompts/chinese/Faithfulness/nli_statements_message_chinese.json

@@ -1,60 +0,0 @@
-{
-  "ragas_version": "0.2.7",
-  "original_hash": 5296785184599215999,
-  "language": "chinese",
-  "instruction": "您的任务是根据给定的上下文判断一系列陈述的真实性。对于每个陈述，如果可以根据上下文直接推断出该陈述，则必须返回判决为1；如果不能根据上下文直接推断出该陈述，则返回判决为0。",
-  "examples": [
-    {
-      "input": {
-        "context": "约翰是XYZ大学的学生。他正在攻读计算机科学学位。本学期他注册了几门课程，包括数据结构、算法和数据库管理。约翰是一个勤奋的学生，花费大量时间学习和完成作业。他经常在图书馆待到很晚以完成他的项目。",
-        "statements": [
-          "约翰主修生物学。",
-          "约翰正在学习一门人工智能课程。",
-          "约翰是一个勤奋的学生。",
-          "约翰有一份兼职工作。"
-        ]
-      },
-      "output": {
-        "statements": [
-          {
-            "statement": "约翰主修生物学。",
-            "reason": "约翰的专业明确提到是计算机科学。没有信息表明他主修生物学。",
-            "verdict": 0
-          },
-          {
-            "statement": "约翰正在学习一门人工智能课程。",
-            "reason": "上下文中提到约翰目前注册的课程，并未提到人工智能。因此，不能推断出约翰正在学习人工智能课程。",
-            "verdict": 0
-          },
-          {
-            "statement": "约翰是一个勤奋的学生。",
-            "reason": "上下文中提到他花费大量时间学习和完成作业。此外，还提到他经常在图书馆待到很晚以完成他的项目，这意味着他很勤奋。",
-            "verdict": 1
-          },
-          {
-            "statement": "约翰有一份兼职工作。",
-            "reason": "上下文中没有给出约翰有兼职工作的信息。",
-            "verdict": 0
-          }
-        ]
-      }
-    },
-    {
-      "input": {
-        "context": "光合作用是植物、藻类和某些细菌用来将光能转化为化学能的过程。",
-        "statements": [
-          "阿尔伯特·爱因斯坦是个天才。"
-        ]
-      },
-      "output": {
-        "statements": [
-          {
-            "statement": "阿尔伯特·爱因斯坦是个天才。",
-            "reason": "上下文和陈述无关",
-            "verdict": 0
-          }
-        ]
-      }
-    }
-  ]
-}

evalscope/backend/rag_eval/ragas/prompts/chinese/Faithfulness/statement_prompt_chinese.json

@@ -1,36 +0,0 @@
-{
-  "ragas_version": "0.2.7",
-  "original_hash": -8546983388246528139,
-  "language": "chinese",
-  "instruction": "给定一个问题、一个答案和答案中的句子，分析在“句子”下给出的每个句子的复杂性，并将每个句子分解为一个或多个完全可理解的陈述，同时确保每个陈述中不使用代词。将输出格式化为JSON。",
-  "examples": [
-    {
-      "input": {
-        "question": "阿尔伯特·爱因斯坦是谁，他最出名的是什么？",
-        "answer": "他是一位出生于德国的理论物理学家，被广泛认为是有史以来最伟大和最有影响力的物理学家之一。他最出名的是发展了相对论，他还为量子力学理论的发展做出了重要贡献。",
-        "sentences": {
-          "0": "他是一位出生于德国的理论物理学家，被广泛认为是有史以来最伟大和最有影响力的物理学家之一。",
-          "1": "他最出名的是发展了相对论，他还为量子力学理论的发展做出了重要贡献。"
-        }
-      },
-      "output": {
-        "sentences": [
-          {
-            "sentence_index": 0,
-            "simpler_statements": [
-              "阿尔伯特·爱因斯坦是一位出生于德国的理论物理学家。",
-              "阿尔伯特·爱因斯坦被认为是有史以来最伟大和最有影响力的物理学家之一。"
-            ]
-          },
-          {
-            "sentence_index": 1,
-            "simpler_statements": [
-              "阿尔伯特·爱因斯坦最出名的是发展了相对论。",
-              "阿尔伯特·爱因斯坦还为量子力学理论的发展做出了重要贡献。"
-            ]
-          }
-        ]
-      }
-    }
-  ]
-}