evalscope 1.0.2__tar.gz → 1.1.1__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of evalscope might be problematic. Click here for more details.
- evalscope-1.1.1/MANIFEST.in +10 -0
- {evalscope-1.0.2/evalscope.egg-info → evalscope-1.1.1}/PKG-INFO +291 -324
- {evalscope-1.0.2 → evalscope-1.1.1}/README.md +188 -318
- evalscope-1.1.1/evalscope/api/benchmark/__init__.py +10 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/benchmark/adapters/__init__.py +1 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/benchmark/adapters/default_data_adapter.py +12 -0
- evalscope-1.1.1/evalscope/api/benchmark/adapters/ner_adapter.py +212 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/benchmark/benchmark.py +14 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/dataset/dataset.py +21 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/dataset/loader.py +6 -2
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/mixin/sandbox_mixin.py +32 -54
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/model/generate_config.py +6 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/app/ui/multi_model.py +6 -1
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/app/ui/single_model.py +8 -2
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/app/utils/data_utils.py +3 -2
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/app/utils/visualization.py +2 -2
- evalscope-1.1.1/evalscope/benchmarks/aa_lcr/aa_lcr_adapter.py +205 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/ai2d/ai2d_adapter.py +3 -2
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bfcl/bfcl_adapter.py +11 -46
- evalscope-1.1.1/evalscope/benchmarks/blink/blink_adapter.py +61 -0
- evalscope-1.1.1/evalscope/benchmarks/chartqa/chartqa_adapter.py +80 -0
- evalscope-1.1.1/evalscope/benchmarks/chartqa/utils.py +38 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/data_collection/data_collection_adapter.py +2 -1
- evalscope-1.1.1/evalscope/benchmarks/docvqa/docvqa_adapter.py +67 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/general_arena/general_arena_adapter.py +1 -1
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/general_arena/utils.py +2 -1
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/general_mcq/general_mcq_adapter.py +1 -1
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/general_qa/general_qa_adapter.py +1 -1
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/gsm8k/gsm8k_adapter.py +23 -4
- evalscope-1.1.1/evalscope/benchmarks/hallusion_bench/hallusion_bench_adapter.py +158 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/hle/hle_adapter.py +3 -2
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/humaneval/humaneval_adapter.py +2 -1
- evalscope-1.1.1/evalscope/benchmarks/infovqa/infovqa_adapter.py +66 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/live_code_bench/live_code_bench_adapter.py +3 -1
- evalscope-1.1.1/evalscope/benchmarks/math_verse/math_verse_adapter.py +100 -0
- evalscope-1.1.1/evalscope/benchmarks/math_vision/math_vision_adapter.py +111 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/math_vista/math_vista_adapter.py +6 -26
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/mm_bench/mm_bench_adapter.py +2 -2
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/mmmu/mmmu_adapter.py +1 -1
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/needle_haystack/needle_haystack_adapter.py +1 -1
- evalscope-1.1.1/evalscope/benchmarks/ner/broad_twitter_corpus_adapter.py +52 -0
- evalscope-1.1.1/evalscope/benchmarks/ner/conll2003_adapter.py +48 -0
- evalscope-1.1.1/evalscope/benchmarks/ner/copious_adapter.py +85 -0
- evalscope-1.1.1/evalscope/benchmarks/ner/cross_ner_adapter.py +120 -0
- evalscope-1.1.1/evalscope/benchmarks/ner/cross_ner_entities/ai.py +54 -0
- evalscope-1.1.1/evalscope/benchmarks/ner/cross_ner_entities/literature.py +36 -0
- evalscope-1.1.1/evalscope/benchmarks/ner/cross_ner_entities/music.py +39 -0
- evalscope-1.1.1/evalscope/benchmarks/ner/cross_ner_entities/politics.py +37 -0
- evalscope-1.1.1/evalscope/benchmarks/ner/cross_ner_entities/science.py +58 -0
- evalscope-1.1.1/evalscope/benchmarks/ner/genia_ner_adapter.py +66 -0
- evalscope-1.1.1/evalscope/benchmarks/ner/harvey_ner_adapter.py +58 -0
- evalscope-1.1.1/evalscope/benchmarks/ner/mit_movie_trivia_adapter.py +74 -0
- evalscope-1.1.1/evalscope/benchmarks/ner/mit_restaurant_adapter.py +66 -0
- evalscope-1.1.1/evalscope/benchmarks/ner/ontonotes5_adapter.py +87 -0
- evalscope-1.1.1/evalscope/benchmarks/ner/wnut2017_adapter.py +61 -0
- evalscope-1.1.1/evalscope/benchmarks/ocr_bench/ocr_bench_adapter.py +101 -0
- evalscope-1.1.1/evalscope/benchmarks/ocr_bench_v2/IoUscore_metric.py +87 -0
- evalscope-1.1.1/evalscope/benchmarks/ocr_bench_v2/TEDS_metric.py +963 -0
- evalscope-1.1.1/evalscope/benchmarks/ocr_bench_v2/ocr_bench_v2_adapter.py +161 -0
- evalscope-1.1.1/evalscope/benchmarks/ocr_bench_v2/page_ocr_metric.py +50 -0
- evalscope-1.1.1/evalscope/benchmarks/ocr_bench_v2/parallel.py +46 -0
- evalscope-1.1.1/evalscope/benchmarks/ocr_bench_v2/spotting_eval/readme.txt +26 -0
- evalscope-1.1.1/evalscope/benchmarks/ocr_bench_v2/spotting_eval/rrc_evaluation_funcs_1_1.py +537 -0
- evalscope-1.1.1/evalscope/benchmarks/ocr_bench_v2/spotting_eval/script.py +481 -0
- evalscope-1.1.1/evalscope/benchmarks/ocr_bench_v2/spotting_metric.py +179 -0
- evalscope-1.1.1/evalscope/benchmarks/ocr_bench_v2/utils.py +433 -0
- evalscope-1.1.1/evalscope/benchmarks/ocr_bench_v2/vqa_metric.py +254 -0
- {evalscope-1.0.2/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models → evalscope-1.1.1/evalscope/benchmarks/omnidoc_bench}/__init__.py +0 -0
- evalscope-1.1.1/evalscope/benchmarks/omnidoc_bench/end2end_eval.py +349 -0
- evalscope-1.1.1/evalscope/benchmarks/omnidoc_bench/metrics.py +547 -0
- evalscope-1.1.1/evalscope/benchmarks/omnidoc_bench/omnidoc_bench_adapter.py +135 -0
- evalscope-1.1.1/evalscope/benchmarks/omnidoc_bench/utils.py +1937 -0
- evalscope-1.1.1/evalscope/benchmarks/poly_math/poly_math_adapter.py +127 -0
- evalscope-1.1.1/evalscope/benchmarks/poly_math/utils/instruction.py +105 -0
- evalscope-1.1.1/evalscope/benchmarks/pope/pope_adapter.py +111 -0
- evalscope-1.1.1/evalscope/benchmarks/seed_bench_2_plus/__init__.py +0 -0
- evalscope-1.1.1/evalscope/benchmarks/seed_bench_2_plus/seed_bench_2_plus_adapter.py +72 -0
- evalscope-1.1.1/evalscope/benchmarks/simple_qa/__init__.py +0 -0
- evalscope-1.1.1/evalscope/benchmarks/simple_vqa/__init__.py +0 -0
- evalscope-1.1.1/evalscope/benchmarks/simple_vqa/simple_vqa_adapter.py +169 -0
- evalscope-1.1.1/evalscope/benchmarks/super_gpqa/__init__.py +0 -0
- evalscope-1.1.1/evalscope/benchmarks/tau_bench/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/tau_bench/tau_bench_adapter.py +1 -1
- evalscope-1.1.1/evalscope/benchmarks/text2image/__init__.py +0 -0
- evalscope-1.1.1/evalscope/benchmarks/tool_bench/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/tool_bench/tool_bench_adapter.py +1 -1
- evalscope-1.1.1/evalscope/benchmarks/visu_logic/__init__.py +0 -0
- evalscope-1.1.1/evalscope/benchmarks/visu_logic/visu_logic_adapter.py +75 -0
- evalscope-1.1.1/evalscope/benchmarks/winogrande/__init__.py +0 -0
- evalscope-1.1.1/evalscope/benchmarks/zerobench/__init__.py +0 -0
- evalscope-1.1.1/evalscope/benchmarks/zerobench/zerobench_adapter.py +64 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/constants.py +4 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/evaluator/evaluator.py +72 -79
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/math_parser.py +14 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/metric.py +52 -1
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/metrics.py +16 -0
- evalscope-1.1.1/evalscope/metrics/t2v_metrics/__init__.py +0 -0
- evalscope-1.1.1/evalscope/metrics/t2v_metrics/models/__init__.py +0 -0
- evalscope-1.1.1/evalscope/metrics/t2v_metrics/models/clipscore_models/build_mps_model/__init__.py +0 -0
- evalscope-1.1.1/evalscope/metrics/t2v_metrics/models/itmscore_models/image_reward/__init__.py +0 -0
- evalscope-1.1.1/evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/Qformer.py +2 -6
- evalscope-1.1.1/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/nlvr_encoder.py +2 -6
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/med.py +2 -6
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/models/utils/openai.py +4 -0
- evalscope-1.1.1/evalscope/perf/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/arguments.py +24 -4
- evalscope-1.1.1/evalscope/perf/benchmark.py +194 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/http_client.py +31 -16
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/main.py +15 -2
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/plugin/api/base.py +9 -7
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/plugin/api/custom_api.py +13 -58
- evalscope-1.1.1/evalscope/perf/plugin/api/default_api.py +205 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/plugin/api/openai_api.py +4 -3
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/plugin/datasets/base.py +21 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/plugin/datasets/custom.py +2 -3
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/plugin/datasets/line_by_line.py +2 -3
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/plugin/datasets/longalpaca.py +2 -3
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/plugin/datasets/openqa.py +2 -4
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/plugin/datasets/random_dataset.py +1 -3
- evalscope-1.1.1/evalscope/perf/utils/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/utils/benchmark_util.py +36 -22
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/utils/db_util.py +14 -19
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/utils/local_server.py +0 -44
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/utils/log_utils.py +21 -6
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/report/__init__.py +11 -2
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/report/combinator.py +52 -2
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/run.py +4 -0
- evalscope-1.1.1/evalscope/third_party/thinkbench/tools/__init__.py +0 -0
- evalscope-1.1.1/evalscope/utils/function_utils.py +253 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/utils/io_utils.py +74 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/utils/json_schema.py +8 -6
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/utils/logger.py +49 -17
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/utils/multi_choices.py +16 -1
- evalscope-1.1.1/evalscope/utils/ner.py +377 -0
- evalscope-1.1.1/evalscope/version.py +4 -0
- {evalscope-1.0.2 → evalscope-1.1.1/evalscope.egg-info}/PKG-INFO +291 -324
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope.egg-info/SOURCES.txt +72 -29
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope.egg-info/requires.txt +4 -29
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope.egg-info/top_level.txt +0 -1
- evalscope-1.1.1/pyproject.toml +61 -0
- evalscope-1.1.1/requirements/sandbox.txt +1 -0
- evalscope-1.1.1/setup.py +4 -0
- evalscope-1.0.2/MANIFEST.in +0 -4
- evalscope-1.0.2/evalscope/api/benchmark/__init__.py +0 -3
- evalscope-1.0.2/evalscope/perf/benchmark.py +0 -209
- evalscope-1.0.2/evalscope/perf/plugin/api/default_api.py +0 -105
- evalscope-1.0.2/evalscope/utils/function_utils.py +0 -70
- evalscope-1.0.2/evalscope/version.py +0 -4
- evalscope-1.0.2/evalscope.egg-info/not-zip-safe +0 -1
- evalscope-1.0.2/requirements.txt +0 -1
- evalscope-1.0.2/setup.py +0 -195
- evalscope-1.0.2/tests/__init__.py +0 -1
- evalscope-1.0.2/tests/benchmark/__init__.py +0 -1
- evalscope-1.0.2/tests/benchmark/test_eval.py +0 -429
- evalscope-1.0.2/tests/benchmark/test_image_edit.py +0 -65
- evalscope-1.0.2/tests/benchmark/test_sandbox.py +0 -81
- evalscope-1.0.2/tests/benchmark/test_t2i.py +0 -142
- evalscope-1.0.2/tests/benchmark/test_vlm.py +0 -137
- evalscope-1.0.2/tests/cli/__init__.py +0 -1
- evalscope-1.0.2/tests/cli/test_all.py +0 -269
- evalscope-1.0.2/tests/cli/test_collection.py +0 -99
- evalscope-1.0.2/tests/cli/test_custom.py +0 -268
- evalscope-1.0.2/tests/cli/test_reasoning.py +0 -81
- evalscope-1.0.2/tests/common.py +0 -73
- evalscope-1.0.2/tests/perf/__init__.py +0 -1
- evalscope-1.0.2/tests/perf/test_perf.py +0 -206
- evalscope-1.0.2/tests/rag/test_clip_benchmark.py +0 -87
- evalscope-1.0.2/tests/rag/test_mteb.py +0 -213
- evalscope-1.0.2/tests/rag/test_ragas.py +0 -128
- evalscope-1.0.2/tests/swift/__init__.py +0 -1
- evalscope-1.0.2/tests/swift/test_run_swift_eval.py +0 -146
- evalscope-1.0.2/tests/swift/test_run_swift_vlm_eval.py +0 -128
- evalscope-1.0.2/tests/swift/test_run_swift_vlm_jugde_eval.py +0 -157
- evalscope-1.0.2/tests/utils.py +0 -13
- evalscope-1.0.2/tests/vlm/__init__.py +0 -1
- evalscope-1.0.2/tests/vlm/test_vlmeval.py +0 -102
- {evalscope-1.0.2 → evalscope-1.1.1}/LICENSE +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/benchmark/adapters/image_edit_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/benchmark/adapters/multi_choice_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/benchmark/adapters/text2image_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/benchmark/adapters/vision_language_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/benchmark/meta.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/dataset/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/dataset/utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/evaluator/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/evaluator/cache.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/evaluator/evaluator.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/evaluator/state.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/filter/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/filter/filter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/messages/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/messages/chat_message.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/messages/content.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/messages/utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/metric/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/metric/metric.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/metric/scorer.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/mixin/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/mixin/llm_judge_mixin.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/model/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/model/model.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/model/model_output.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/registry.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/tool/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/tool/tool_call.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/tool/tool_info.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/api/tool/utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/app/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/app/app.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/app/arguments.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/app/constants.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/app/ui/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/app/ui/app_ui.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/app/ui/sidebar.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/app/ui/visualization.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/app/utils/env_utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/app/utils/localization.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/app/utils/text_utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/arguments.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/base.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/opencompass/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/opencompass/api_meta_template.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/opencompass/backend_manager.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/opencompass/tasks/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/opencompass/tasks/eval_api.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/opencompass/tasks/eval_datasets.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/backend_manager.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/clip_benchmark/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/clip_benchmark/arguments.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/clip_benchmark/dataset_builder.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/clip_benchmark/task_template.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/clip_benchmark/tasks/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/clip_benchmark/tasks/image_caption.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/clip_benchmark/tasks/zeroshot_classification.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/clip_benchmark/tasks/zeroshot_retrieval.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/clip_benchmark/utils/webdataset_convert.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/clip_benchmark/utils/webdatasets.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/cmteb/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/cmteb/arguments.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/cmteb/base.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/cmteb/task_template.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/cmteb/tasks/Classification.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/cmteb/tasks/Clustering.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/cmteb/tasks/CustomTask.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/cmteb/tasks/PairClassification.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/cmteb/tasks/Reranking.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/cmteb/tasks/Retrieval.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/cmteb/tasks/STS.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/cmteb/tasks/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/ragas/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/ragas/arguments.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/ragas/prompts/persona_prompt.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/ragas/task_template.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/ragas/tasks/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/ragas/tasks/build_distribution.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/ragas/tasks/build_transform.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/ragas/tasks/testset_generation.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/ragas/tasks/translate_prompt.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/utils/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/utils/clip.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/utils/embedding.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/utils/llm.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/rag_eval/utils/tools.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/vlm_eval_kit/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/backend/vlm_eval_kit/backend_manager.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/__init__.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/ai2d → evalscope-1.1.1/evalscope/benchmarks/aa_lcr}/__init__.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/aime → evalscope-1.1.1/evalscope/benchmarks/ai2d}/__init__.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/alpaca_eval → evalscope-1.1.1/evalscope/benchmarks/aime}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/aime/aime24_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/aime/aime25_adapter.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/amc → evalscope-1.1.1/evalscope/benchmarks/alpaca_eval}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/alpaca_eval/alpaca_eval_adapter.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/arena_hard → evalscope-1.1.1/evalscope/benchmarks/amc}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/amc/amc_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/arc/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/arc/arc_adapter.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/bfcl → evalscope-1.1.1/evalscope/benchmarks/arena_hard}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/arena_hard/arena_hard_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/arena_hard/utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/bbh_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/boolean_expressions.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/causal_judgement.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/date_understanding.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/disambiguation_qa.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/dyck_languages.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/formal_fallacies.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/geometric_shapes.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/hyperbaton.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/logical_deduction_five_objects.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/logical_deduction_seven_objects.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/logical_deduction_three_objects.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/movie_recommendation.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/multistep_arithmetic_two.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/navigate.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/object_counting.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/penguins_in_a_table.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/reasoning_about_colored_objects.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/ruin_names.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/salient_translation_error_detection.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/snarks.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/sports_understanding.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/temporal_sequences.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/tracking_shuffled_objects_five_objects.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/tracking_shuffled_objects_seven_objects.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/tracking_shuffled_objects_three_objects.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/web_of_lies.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bbh/cot_prompts/word_sorting.txt +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/chinese_simple_qa → evalscope-1.1.1/evalscope/benchmarks/bfcl}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/bfcl/generation.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/data_collection → evalscope-1.1.1/evalscope/benchmarks/blink}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/ceval/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/ceval/ceval_adapter.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/docmath → evalscope-1.1.1/evalscope/benchmarks/chartqa}/__init__.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/drop → evalscope-1.1.1/evalscope/benchmarks/chinese_simple_qa}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/chinese_simple_qa/csimple_qa_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/cmmlu/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/cmmlu/cmmlu_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/competition_math/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/competition_math/competition_math_adapter.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/frames → evalscope-1.1.1/evalscope/benchmarks/data_collection}/__init__.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/general_arena → evalscope-1.1.1/evalscope/benchmarks/docmath}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/docmath/docmath_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/docmath/utils.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/general_mcq → evalscope-1.1.1/evalscope/benchmarks/docvqa}/__init__.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/gpqa → evalscope-1.1.1/evalscope/benchmarks/drop}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/drop/drop_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/drop/utils.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/healthbench → evalscope-1.1.1/evalscope/benchmarks/frames}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/frames/frames_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/frames/utils.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/hle → evalscope-1.1.1/evalscope/benchmarks/general_arena}/__init__.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/ifeval → evalscope-1.1.1/evalscope/benchmarks/general_mcq}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/general_qa/__init__.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/image_edit → evalscope-1.1.1/evalscope/benchmarks/gpqa}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/gpqa/gpqa_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/gpqa/prompt.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/gsm8k/__init__.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/image_edit/gedit → evalscope-1.1.1/evalscope/benchmarks/hallusion_bench}/__init__.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/iquiz → evalscope-1.1.1/evalscope/benchmarks/healthbench}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/healthbench/healthbench_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/healthbench/utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/hellaswag/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/hellaswag/hellaswag_adapter.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/live_code_bench → evalscope-1.1.1/evalscope/benchmarks/hle}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/humaneval/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/humaneval/utils.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/maritime_bench → evalscope-1.1.1/evalscope/benchmarks/ifeval}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/ifeval/ifeval_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/ifeval/instructions.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/ifeval/instructions_registry.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/ifeval/instructions_util.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/ifeval/utils.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/math_500 → evalscope-1.1.1/evalscope/benchmarks/image_edit}/__init__.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/math_vista → evalscope-1.1.1/evalscope/benchmarks/image_edit/gedit}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/image_edit/gedit/gedit_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/image_edit/gedit/utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/image_edit/gedit/vie_prompts.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/minerva_math → evalscope-1.1.1/evalscope/benchmarks/infovqa}/__init__.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/mm_bench → evalscope-1.1.1/evalscope/benchmarks/iquiz}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/iquiz/iquiz_adapter.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/mm_star → evalscope-1.1.1/evalscope/benchmarks/live_code_bench}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/live_code_bench/evaluate_utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/live_code_bench/extract_utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/live_code_bench/load_utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/live_code_bench/pass_k_utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/live_code_bench/prompts.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/live_code_bench/sandbox_evaluate_utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/live_code_bench/testing_util.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/mmlu_pro → evalscope-1.1.1/evalscope/benchmarks/maritime_bench}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/maritime_bench/maritime_bench_adapter.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/mmlu_redux → evalscope-1.1.1/evalscope/benchmarks/math_500}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/math_500/math_500_adapter.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/mmmu → evalscope-1.1.1/evalscope/benchmarks/math_verse}/__init__.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/mmmu_pro → evalscope-1.1.1/evalscope/benchmarks/math_vision}/__init__.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/multi_if → evalscope-1.1.1/evalscope/benchmarks/math_vista}/__init__.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/musr → evalscope-1.1.1/evalscope/benchmarks/minerva_math}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/minerva_math/minerva_math_adapter.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/needle_haystack → evalscope-1.1.1/evalscope/benchmarks/mm_bench}/__init__.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/olympiad_bench → evalscope-1.1.1/evalscope/benchmarks/mm_star}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/mm_star/mm_star_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/mmlu/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/mmlu/mmlu_adapter.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/omni_bench → evalscope-1.1.1/evalscope/benchmarks/mmlu_pro}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/mmlu_pro/mmlu_pro_adapter.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/process_bench → evalscope-1.1.1/evalscope/benchmarks/mmlu_redux}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/mmlu_redux/mmlu_redux_adapter.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/real_world_qa → evalscope-1.1.1/evalscope/benchmarks/mmmu}/__init__.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/simple_qa → evalscope-1.1.1/evalscope/benchmarks/mmmu_pro}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/mmmu_pro/mmmu_pro_adapter.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/super_gpqa → evalscope-1.1.1/evalscope/benchmarks/multi_if}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/multi_if/ifeval.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/multi_if/metrics.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/multi_if/multi_if_adapter.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/tau_bench → evalscope-1.1.1/evalscope/benchmarks/musr}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/musr/musr_adapter.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/text2image → evalscope-1.1.1/evalscope/benchmarks/needle_haystack}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/needle_haystack/utils.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/tool_bench → evalscope-1.1.1/evalscope/benchmarks/ner}/__init__.py +0 -0
- {evalscope-1.0.2/evalscope/benchmarks/winogrande → evalscope-1.1.1/evalscope/benchmarks/ner/cross_ner_entities}/__init__.py +0 -0
- {evalscope-1.0.2/evalscope/metrics/t2v_metrics → evalscope-1.1.1/evalscope/benchmarks/ocr_bench}/__init__.py +0 -0
- {evalscope-1.0.2/evalscope/metrics/t2v_metrics/models → evalscope-1.1.1/evalscope/benchmarks/ocr_bench_v2}/__init__.py +0 -0
- {evalscope-1.0.2/evalscope/metrics/t2v_metrics/models/clipscore_models/build_mps_model → evalscope-1.1.1/evalscope/benchmarks/ocr_bench_v2/spotting_eval}/__init__.py +0 -0
- {evalscope-1.0.2/evalscope/metrics/t2v_metrics/models/itmscore_models/image_reward → evalscope-1.1.1/evalscope/benchmarks/olympiad_bench}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/olympiad_bench/olympiad_bench_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/olympiad_bench/utils.py +0 -0
- {evalscope-1.0.2/evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5 → evalscope-1.1.1/evalscope/benchmarks/omni_bench}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/omni_bench/omni_bench_adapter.py +0 -0
- {evalscope-1.0.2/evalscope/perf → evalscope-1.1.1/evalscope/benchmarks/poly_math}/__init__.py +0 -0
- {evalscope-1.0.2/evalscope/perf/utils → evalscope-1.1.1/evalscope/benchmarks/pope}/__init__.py +0 -0
- {evalscope-1.0.2/evalscope/third_party/thinkbench/tools → evalscope-1.1.1/evalscope/benchmarks/process_bench}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/process_bench/process_bench_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/race/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/race/race_adapter.py +0 -0
- {evalscope-1.0.2/tests/rag → evalscope-1.1.1/evalscope/benchmarks/real_world_qa}/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/real_world_qa/real_world_qa_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/simple_qa/simple_qa_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/super_gpqa/prompt.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/super_gpqa/super_gpqa_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/super_gpqa/utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/tau_bench/generation.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/text2image/evalmuse_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/text2image/genai_bench_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/text2image/general_t2i_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/text2image/hpdv2_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/text2image/tifa_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/tool_bench/utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/trivia_qa/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/trivia_qa/samples.jsonl +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/trivia_qa/trivia_qa_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/truthful_qa/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/truthful_qa/truthful_qa_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/benchmarks/winogrande/winogrande_adapter.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/cli/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/cli/base.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/cli/cli.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/cli/start_app.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/cli/start_eval.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/cli/start_perf.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/cli/start_server.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/collections/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/collections/sampler.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/collections/schema.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/config.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/evaluator/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/filters/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/filters/extraction.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/filters/selection.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/bundled_rouge_score/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/bundled_rouge_score/rouge_scorer.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/llm_judge.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/rouge_metric.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/clipscore.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/constants.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/itmscore.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/clipscore_models/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/clipscore_models/build_mps_model/base_model.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/clipscore_models/build_mps_model/clip_model.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/clipscore_models/build_mps_model/cross_modeling.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/clipscore_models/clip_model.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/clipscore_models/hpsv2_model.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/clipscore_models/mps_model.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/clipscore_models/pickscore_model.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/itmscore_models/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/itmscore_models/blip2_itm_model.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/itmscore_models/fga_blip2_model.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/itmscore_models/image_reward/ImageReward.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/itmscore_models/image_reward/blip_pretrain.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/itmscore_models/image_reward_model.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/model.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5/model/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5/model/language_model/clip_t5.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5/model/multimodal_encoder/builder.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5/model/multimodal_encoder/clip_encoder.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5/model/multimodal_projector/builder.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/clip_t5_model.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/gpt4v_model.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/config.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/dist_utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/gradcam.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/logger.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/optims.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/registry.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/vqa_tools/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/vqa_tools/vqa.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/common/vqa_tools/vqa_eval.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/default.yaml +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_caption_flant5xl.yaml +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_caption_opt2.7b.yaml +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_caption_opt6.7b.yaml +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_coco.yaml +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_instruct_flant5xl.yaml +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_instruct_flant5xxl.yaml +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_instruct_vicuna13b.yaml +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_instruct_vicuna7b.yaml +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain.yaml +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_flant5xl.yaml +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_flant5xl_iter_80k_total_100k_no_prefix.yaml +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_flant5xl_iter_80k_total_100k_prefix.yaml +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_flant5xl_vitL.yaml +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_flant5xxl.yaml +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_opt2.7b.yaml +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_opt6.7b.yaml +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_pretrain_vitL.yaml +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_vicuna13b.yaml +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/blip2/blip2_vicuna7b.yaml +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/med_config.json +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/med_config_albef.json +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/configs/models/med_large_config.json +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/base_model.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2_image_text_matching.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2_qformer.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2_t5.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/blip2_t5_instruct.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/fga_blip2.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/modeling_llama.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip2_models/modeling_t5.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_caption.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_classification.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_feature_extractor.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_image_text_matching.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_nlvr.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_outputs.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_pretrain.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/blip_models/blip_vqa.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/clip_vit.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/eva_vit.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/models/vit.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/processors/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/processors/base_processor.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/processors/blip_processors.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/lavis/processors/randaugment.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/mm_utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/models/vqascore_models/vqa_model.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/score.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/metrics/t2v_metrics/vqascore.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/models/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/models/image_edit_model.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/models/mockllm.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/models/model_apis.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/models/modelscope.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/models/openai_compatible.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/models/text2image_model.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/plugin/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/plugin/api/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/plugin/api/dashscope_api.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/plugin/datasets/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/plugin/datasets/flickr8k.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/plugin/datasets/kontext_bench.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/plugin/datasets/random_vl_dataset.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/plugin/datasets/speed_benchmark.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/plugin/registry.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/utils/analysis_result.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/utils/handler.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/perf/utils/rich_display.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/report/generator.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/report/report.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/summarizer.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/longbench_write/README.md +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/longbench_write/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/longbench_write/default_task.json +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/longbench_write/default_task.yaml +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/longbench_write/eval.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/longbench_write/infer.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/longbench_write/longbench_write.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/longbench_write/resources/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/longbench_write/resources/judge.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/longbench_write/resources/longbench_write.jsonl +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/longbench_write/resources/longbench_write_en.jsonl +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/longbench_write/resources/longwrite_ruler.jsonl +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/longbench_write/tools/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/longbench_write/tools/data_etl.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/longbench_write/tools/openai_api.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/longbench_write/utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/thinkbench/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/thinkbench/eval.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/thinkbench/infer.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/thinkbench/resources/critique_template.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/thinkbench/resources/reformat_template.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/thinkbench/tools/llm.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/thinkbench/tools/utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/toolbench_static/README.md +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/toolbench_static/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/toolbench_static/config_default.json +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/toolbench_static/config_default.yaml +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/toolbench_static/eval.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/toolbench_static/infer.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/toolbench_static/llm/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/toolbench_static/llm/swift_infer.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/toolbench_static/requirements.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/third_party/toolbench_static/toolbench_static.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/utils/__init__.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/utils/argument_utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/utils/chat_service.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/utils/deprecation_utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/utils/import_utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/utils/model_utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope/utils/url_utils.py +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope.egg-info/dependency_links.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/evalscope.egg-info/entry_points.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/requirements/aigc.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/requirements/app.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/requirements/dev.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/requirements/docs.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/requirements/framework.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/requirements/opencompass.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/requirements/perf.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/requirements/rag.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/requirements/vlmeval.txt +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/setup.cfg +0 -0
- {evalscope-1.0.2 → evalscope-1.1.1}/tests/test_run_all.py +0 -0
|
@@ -0,0 +1,10 @@
|
|
|
1
|
+
include README.md
|
|
2
|
+
|
|
3
|
+
# Include all resources (code + other files) inside the package
|
|
4
|
+
recursive-include evalscope *
|
|
5
|
+
|
|
6
|
+
# Exclude cache/compiled artifacts
|
|
7
|
+
global-exclude *.py[cod] __pycache__ *.so *.dylib
|
|
8
|
+
|
|
9
|
+
# If there are models/large files, you can add prune/exclude as needed
|
|
10
|
+
# Example: prune evalscope/models
|