LICENSE
MANIFEST.in
pyproject.toml
setup.py
dc_lms.egg-info/PKG-INFO
dc_lms.egg-info/SOURCES.txt
dc_lms.egg-info/dependency_links.txt
dc_lms.egg-info/entry_points.txt
dc_lms.egg-info/requires.txt
dc_lms.egg-info/top_level.txt
lms/client/__init__.py
lms/client/common_utils.py
lms/client/config.py
lms/client/deploy_module.py
lms/client/evaluate_module.py
lms/client/help_constants.py
lms/client/import_module.py
lms/client/main.py
lms/client/network_utils.py
lms/client/prune_module.py
lms/client/quantize_module.py
lms/client/validaters.py
lms/client/cluster/__init__.py
lms/client/cluster/adm.py
lms/client/daemon/__init__.py
lms/client/daemon/main.py
lms/client/daemon/nvml_util.py
lms/client/daemon/serving.py
lms/runtime/__init__.py
lms/runtime/main.py
lms/runtime/common/__init__.py
lms/runtime/common/common_utils.py
lms/runtime/common/pipeline_loader_example.py
lms/runtime/common/test.py
lms/runtime/common/traceback_utils.py
lms/runtime/deploy/__init__.py
lms/runtime/deploy/deepspeed_infer.py
lms/runtime/deploy/request.py
lms/runtime/deploy/request_body.json
lms/runtime/deploy/serving.py
lms/runtime/deploy/transformers_infer.py
lms/runtime/evaluation/__init__.py
lms/runtime/evaluation/accuracy.py
lms/runtime/evaluation/eval_module.py
lms/runtime/evaluation/manual_eval.py
lms/runtime/evaluation/benchmark/__init__.py
lms/runtime/evaluation/benchmark/accuracy.py
lms/runtime/evaluation/benchmark/dataset_loader.py
lms/runtime/evaluation/benchmark/eval.py
lms/runtime/evaluation/benchmark/eval_dataset.py
lms/runtime/evaluation/benchmark/eval_metric.py
lms/runtime/evaluation/benchmark/eval_ppl.py
lms/runtime/evaluation/benchmark/data/__init__.py
lms/runtime/evaluation/benchmark/data/AGIEval/data/few_shot_prompts.csv
lms/runtime/evaluation/benchmark/data/AGIEval/data/v1/LICENSE
lms/runtime/evaluation/benchmark/data/AGIEval/data/v1/aqua-rat.jsonl
lms/runtime/evaluation/benchmark/data/AGIEval/data/v1/gaokao-biology.jsonl
lms/runtime/evaluation/benchmark/data/AGIEval/data/v1/gaokao-chemistry.jsonl
lms/runtime/evaluation/benchmark/data/AGIEval/data/v1/gaokao-chinese.jsonl
lms/runtime/evaluation/benchmark/data/AGIEval/data/v1/gaokao-english.jsonl
lms/runtime/evaluation/benchmark/data/AGIEval/data/v1/gaokao-geography.jsonl
lms/runtime/evaluation/benchmark/data/AGIEval/data/v1/gaokao-history.jsonl
lms/runtime/evaluation/benchmark/data/AGIEval/data/v1/gaokao-mathcloze.jsonl
lms/runtime/evaluation/benchmark/data/AGIEval/data/v1/gaokao-mathqa.jsonl
lms/runtime/evaluation/benchmark/data/AGIEval/data/v1/gaokao-physics.jsonl
lms/runtime/evaluation/benchmark/data/AGIEval/data/v1/gaokao-physics.jsonl.all
lms/runtime/evaluation/benchmark/data/AGIEval/data/v1/jec-qa-ca.jsonl
lms/runtime/evaluation/benchmark/data/AGIEval/data/v1/jec-qa-kd.jsonl
lms/runtime/evaluation/benchmark/data/AGIEval/data/v1/logiqa-en.jsonl
lms/runtime/evaluation/benchmark/data/AGIEval/data/v1/logiqa-zh.jsonl
lms/runtime/evaluation/benchmark/data/AGIEval/data/v1/lsat-ar.jsonl
lms/runtime/evaluation/benchmark/data/AGIEval/data/v1/lsat-lr.jsonl
lms/runtime/evaluation/benchmark/data/AGIEval/data/v1/lsat-rc.jsonl
lms/runtime/evaluation/benchmark/data/AGIEval/data/v1/math.jsonl
lms/runtime/evaluation/benchmark/data/AGIEval/data/v1/sat-en-without-passage.jsonl
lms/runtime/evaluation/benchmark/data/AGIEval/data/v1/sat-en.jsonl
lms/runtime/evaluation/benchmark/data/AGIEval/data/v1/sat-math.jsonl
lms/runtime/evaluation/benchmark/data/ARC/ARC-c/ARC-Challenge-Dev.jsonl
lms/runtime/evaluation/benchmark/data/ARC/ARC-c/ARC-Challenge-Test.jsonl
lms/runtime/evaluation/benchmark/data/ARC/ARC-e/ARC-Easy-Dev.jsonl
lms/runtime/evaluation/benchmark/data/ARC/ARC-e/ARC-Easy-Test.jsonl
lms/runtime/evaluation/benchmark/data/BBH/data/README.md
lms/runtime/evaluation/benchmark/data/BBH/data/boolean_expressions.json
lms/runtime/evaluation/benchmark/data/BBH/data/causal_judgement.json
lms/runtime/evaluation/benchmark/data/BBH/data/date_understanding.json
lms/runtime/evaluation/benchmark/data/BBH/data/disambiguation_qa.json
lms/runtime/evaluation/benchmark/data/BBH/data/dyck_languages.json
lms/runtime/evaluation/benchmark/data/BBH/data/formal_fallacies.json
lms/runtime/evaluation/benchmark/data/BBH/data/geometric_shapes.json
lms/runtime/evaluation/benchmark/data/BBH/data/hyperbaton.json
lms/runtime/evaluation/benchmark/data/BBH/data/logical_deduction_five_objects.json
lms/runtime/evaluation/benchmark/data/BBH/data/logical_deduction_seven_objects.json
lms/runtime/evaluation/benchmark/data/BBH/data/logical_deduction_three_objects.json
lms/runtime/evaluation/benchmark/data/BBH/data/movie_recommendation.json
lms/runtime/evaluation/benchmark/data/BBH/data/multistep_arithmetic_two.json
lms/runtime/evaluation/benchmark/data/BBH/data/navigate.json
lms/runtime/evaluation/benchmark/data/BBH/data/object_counting.json
lms/runtime/evaluation/benchmark/data/BBH/data/penguins_in_a_table.json
lms/runtime/evaluation/benchmark/data/BBH/data/reasoning_about_colored_objects.json
lms/runtime/evaluation/benchmark/data/BBH/data/ruin_names.json
lms/runtime/evaluation/benchmark/data/BBH/data/salient_translation_error_detection.json
lms/runtime/evaluation/benchmark/data/BBH/data/snarks.json
lms/runtime/evaluation/benchmark/data/BBH/data/sports_understanding.json
lms/runtime/evaluation/benchmark/data/BBH/data/temporal_sequences.json
lms/runtime/evaluation/benchmark/data/BBH/data/tracking_shuffled_objects_five_objects.json
lms/runtime/evaluation/benchmark/data/BBH/data/tracking_shuffled_objects_seven_objects.json
lms/runtime/evaluation/benchmark/data/BBH/data/tracking_shuffled_objects_three_objects.json
lms/runtime/evaluation/benchmark/data/BBH/data/web_of_lies.json
lms/runtime/evaluation/benchmark/data/BBH/data/word_sorting.json
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/boolean_expressions.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/causal_judgement.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/date_understanding.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/disambiguation_qa.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/dyck_languages.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/formal_fallacies.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/geometric_shapes.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/hyperbaton.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/logical_deduction_five_objects.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/logical_deduction_seven_objects.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/logical_deduction_three_objects.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/movie_recommendation.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/multistep_arithmetic_two.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/navigate.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/object_counting.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/penguins_in_a_table.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/reasoning_about_colored_objects.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/ruin_names.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/salient_translation_error_detection.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/snarks.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/sports_understanding.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/temporal_sequences.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/tracking_shuffled_objects_five_objects.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/tracking_shuffled_objects_seven_objects.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/tracking_shuffled_objects_three_objects.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/web_of_lies.txt
lms/runtime/evaluation/benchmark/data/BBH/lib_prompt/word_sorting.txt
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/accountant_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/advanced_mathematics_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/art_studies_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/basic_medicine_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/business_administration_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/chinese_language_and_literature_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/civil_servant_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/clinical_medicine_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/college_chemistry_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/college_economics_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/college_physics_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/college_programming_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/computer_architecture_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/computer_network_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/discrete_mathematics_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/education_science_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/electrical_engineer_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/environmental_impact_assessment_engineer_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/fire_engineer_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/high_school_biology_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/high_school_chemistry_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/high_school_chinese_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/high_school_geography_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/high_school_history_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/high_school_mathematics_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/high_school_physics_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/high_school_politics_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/ideological_and_moral_cultivation_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/law_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/legal_professional_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/logic_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/mao_zedong_thought_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/marxism_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/metrology_engineer_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/middle_school_biology_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/middle_school_chemistry_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/middle_school_geography_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/middle_school_history_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/middle_school_mathematics_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/middle_school_physics_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/middle_school_politics_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/modern_chinese_history_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/operating_system_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/physician_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/plant_protection_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/probability_and_statistics_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/professional_tour_guide_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/sports_science_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/tax_accountant_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/teacher_qualification_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/urban_and_rural_planner_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/dev/veterinary_medicine_dev.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/accountant_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/advanced_mathematics_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/art_studies_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/basic_medicine_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/business_administration_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/chinese_language_and_literature_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/civil_servant_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/clinical_medicine_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/college_chemistry_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/college_economics_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/college_physics_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/college_programming_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/computer_architecture_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/computer_network_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/discrete_mathematics_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/education_science_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/electrical_engineer_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/environmental_impact_assessment_engineer_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/fire_engineer_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/high_school_biology_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/high_school_chemistry_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/high_school_chinese_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/high_school_geography_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/high_school_history_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/high_school_mathematics_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/high_school_physics_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/high_school_politics_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/ideological_and_moral_cultivation_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/law_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/legal_professional_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/logic_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/mao_zedong_thought_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/marxism_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/metrology_engineer_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/middle_school_biology_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/middle_school_chemistry_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/middle_school_geography_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/middle_school_history_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/middle_school_mathematics_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/middle_school_physics_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/middle_school_politics_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/modern_chinese_history_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/operating_system_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/physician_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/plant_protection_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/probability_and_statistics_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/professional_tour_guide_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/sports_science_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/tax_accountant_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/teacher_qualification_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/urban_and_rural_planner_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/test/veterinary_medicine_test.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/accountant_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/advanced_mathematics_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/art_studies_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/basic_medicine_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/business_administration_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/chinese_language_and_literature_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/civil_servant_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/clinical_medicine_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/college_chemistry_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/college_economics_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/college_physics_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/college_programming_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/computer_architecture_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/computer_network_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/discrete_mathematics_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/education_science_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/electrical_engineer_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/environmental_impact_assessment_engineer_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/fire_engineer_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/high_school_biology_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/high_school_chemistry_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/high_school_chinese_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/high_school_geography_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/high_school_history_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/high_school_mathematics_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/high_school_physics_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/high_school_politics_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/ideological_and_moral_cultivation_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/law_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/legal_professional_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/logic_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/mao_zedong_thought_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/marxism_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/metrology_engineer_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/middle_school_biology_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/middle_school_chemistry_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/middle_school_geography_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/middle_school_history_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/middle_school_mathematics_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/middle_school_physics_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/middle_school_politics_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/modern_chinese_history_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/operating_system_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/physician_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/plant_protection_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/probability_and_statistics_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/professional_tour_guide_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/sports_science_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/tax_accountant_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/teacher_qualification_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/urban_and_rural_planner_val.csv
lms/runtime/evaluation/benchmark/data/ceval/formal_ceval/val/veterinary_medicine_val.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/agronomy.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/anatomy.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/ancient_chinese.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/arts.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/astronomy.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/business_ethics.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/chinese_civil_service_exam.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/chinese_driving_rule.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/chinese_food_culture.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/chinese_foreign_policy.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/chinese_history.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/chinese_literature.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/chinese_teacher_qualification.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/clinical_knowledge.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/college_actuarial_science.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/college_education.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/college_engineering_hydrology.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/college_law.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/college_mathematics.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/college_medical_statistics.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/college_medicine.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/computer_science.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/computer_security.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/conceptual_physics.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/construction_project_management.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/economics.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/education.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/electrical_engineering.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/elementary_chinese.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/elementary_commonsense.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/elementary_information_and_technology.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/elementary_mathematics.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/ethnology.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/food_science.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/genetics.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/global_facts.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/high_school_biology.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/high_school_chemistry.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/high_school_geography.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/high_school_mathematics.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/high_school_physics.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/high_school_politics.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/human_sexuality.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/international_law.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/journalism.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/jurisprudence.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/legal_and_moral_basis.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/logical.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/machine_learning.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/management.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/marketing.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/marxist_theory.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/modern_chinese.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/nutrition.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/philosophy.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/professional_accounting.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/professional_law.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/professional_medicine.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/professional_psychology.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/public_relations.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/security_study.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/sociology.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/sports_science.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/traditional_chinese_medicine.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/virology.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/world_history.csv
lms/runtime/evaluation/benchmark/data/cmmlu/dev/world_religions.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/agronomy.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/anatomy.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/ancient_chinese.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/arts.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/astronomy.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/business_ethics.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/chinese_civil_service_exam.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/chinese_driving_rule.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/chinese_food_culture.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/chinese_foreign_policy.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/chinese_history.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/chinese_literature.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/chinese_teacher_qualification.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/clinical_knowledge.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/college_actuarial_science.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/college_education.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/college_engineering_hydrology.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/college_law.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/college_mathematics.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/college_medical_statistics.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/college_medicine.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/computer_science.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/computer_security.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/conceptual_physics.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/construction_project_management.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/economics.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/education.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/electrical_engineering.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/elementary_chinese.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/elementary_commonsense.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/elementary_information_and_technology.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/elementary_mathematics.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/ethnology.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/food_science.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/genetics.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/global_facts.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/high_school_biology.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/high_school_chemistry.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/high_school_geography.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/high_school_mathematics.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/high_school_physics.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/high_school_politics.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/human_sexuality.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/international_law.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/journalism.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/jurisprudence.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/legal_and_moral_basis.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/logical.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/machine_learning.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/management.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/marketing.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/marxist_theory.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/modern_chinese.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/nutrition.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/philosophy.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/professional_accounting.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/professional_law.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/professional_medicine.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/professional_psychology.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/public_relations.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/security_study.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/sociology.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/sports_science.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/traditional_chinese_medicine.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/virology.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/world_history.csv
lms/runtime/evaluation/benchmark/data/cmmlu/test/world_religions.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/abstract_algebra_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/anatomy_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/astronomy_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/business_ethics_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/clinical_knowledge_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/college_biology_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/college_chemistry_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/college_computer_science_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/college_mathematics_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/college_medicine_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/college_physics_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/computer_security_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/conceptual_physics_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/econometrics_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/electrical_engineering_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/elementary_mathematics_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/formal_logic_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/global_facts_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/high_school_biology_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/high_school_chemistry_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/high_school_computer_science_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/high_school_european_history_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/high_school_geography_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/high_school_government_and_politics_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/high_school_macroeconomics_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/high_school_mathematics_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/high_school_microeconomics_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/high_school_physics_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/high_school_psychology_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/high_school_statistics_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/high_school_us_history_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/high_school_world_history_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/human_aging_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/human_sexuality_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/international_law_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/jurisprudence_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/logical_fallacies_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/machine_learning_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/management_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/marketing_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/medical_genetics_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/miscellaneous_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/moral_disputes_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/moral_scenarios_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/nutrition_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/philosophy_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/prehistory_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/professional_accounting_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/professional_law_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/professional_medicine_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/professional_psychology_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/public_relations_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/security_studies_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/sociology_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/us_foreign_policy_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/virology_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/dev/world_religions_dev.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/abstract_algebra_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/anatomy_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/astronomy_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/business_ethics_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/clinical_knowledge_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/college_biology_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/college_chemistry_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/college_computer_science_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/college_mathematics_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/college_medicine_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/college_physics_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/computer_security_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/conceptual_physics_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/econometrics_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/electrical_engineering_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/elementary_mathematics_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/formal_logic_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/global_facts_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/high_school_biology_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/high_school_chemistry_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/high_school_computer_science_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/high_school_european_history_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/high_school_geography_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/high_school_government_and_politics_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/high_school_macroeconomics_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/high_school_mathematics_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/high_school_microeconomics_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/high_school_physics_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/high_school_psychology_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/high_school_statistics_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/high_school_us_history_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/high_school_world_history_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/human_aging_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/human_sexuality_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/international_law_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/jurisprudence_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/logical_fallacies_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/machine_learning_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/management_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/marketing_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/medical_genetics_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/miscellaneous_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/moral_disputes_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/moral_scenarios_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/nutrition_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/philosophy_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/prehistory_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/professional_accounting_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/professional_law_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/professional_medicine_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/professional_psychology_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/public_relations_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/security_studies_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/sociology_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/us_foreign_policy_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/virology_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/test/world_religions_test.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/abstract_algebra_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/anatomy_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/astronomy_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/business_ethics_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/clinical_knowledge_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/college_biology_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/college_chemistry_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/college_computer_science_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/college_mathematics_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/college_medicine_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/college_physics_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/computer_security_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/conceptual_physics_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/econometrics_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/electrical_engineering_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/elementary_mathematics_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/formal_logic_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/global_facts_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/high_school_biology_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/high_school_chemistry_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/high_school_computer_science_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/high_school_european_history_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/high_school_geography_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/high_school_government_and_politics_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/high_school_macroeconomics_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/high_school_mathematics_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/high_school_microeconomics_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/high_school_physics_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/high_school_psychology_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/high_school_statistics_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/high_school_us_history_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/high_school_world_history_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/human_aging_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/human_sexuality_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/international_law_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/jurisprudence_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/logical_fallacies_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/machine_learning_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/management_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/marketing_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/medical_genetics_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/miscellaneous_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/moral_disputes_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/moral_scenarios_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/nutrition_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/philosophy_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/prehistory_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/professional_accounting_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/professional_law_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/professional_medicine_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/professional_psychology_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/public_relations_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/security_studies_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/sociology_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/us_foreign_policy_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/virology_val.csv
lms/runtime/evaluation/benchmark/data/mmlu/val/world_religions_val.csv
lms/runtime/evaluation/custom/__init__.py
lms/runtime/evaluation/custom/eval.py
lms/runtime/evaluation/custom/example.py
lms/runtime/prune/__init__.py
lms/runtime/prune/llm_pruner/__init__.py
lms/runtime/prune/llm_pruner/baichuan.py
lms/runtime/prune/llm_pruner/bloom.py
lms/runtime/prune/llm_pruner/entry.py
lms/runtime/prune/llm_pruner/hf_prune.py
lms/runtime/prune/llm_pruner/util.py
lms/runtime/prune/llm_pruner/LLMPruner/__init__.py
lms/runtime/prune/llm_pruner/LLMPruner/datasets/dialogue.py
lms/runtime/prune/llm_pruner/LLMPruner/datasets/example_samples.py
lms/runtime/prune/llm_pruner/LLMPruner/datasets/ppl_dataset.py
lms/runtime/prune/llm_pruner/LLMPruner/evaluator/ppl.py
lms/runtime/prune/llm_pruner/LLMPruner/models/__init__.py
lms/runtime/prune/llm_pruner/LLMPruner/models/helper.py
lms/runtime/prune/llm_pruner/LLMPruner/models/hf_baichuan/__init__.py
lms/runtime/prune/llm_pruner/LLMPruner/models/hf_baichuan/baichuan13B/configuration_baichuan.py
lms/runtime/prune/llm_pruner/LLMPruner/models/hf_baichuan/baichuan13B/modeling_baichuan_13B.py
lms/runtime/prune/llm_pruner/LLMPruner/models/hf_baichuan/baichuan7B/configuration_baichuan.py
lms/runtime/prune/llm_pruner/LLMPruner/models/hf_baichuan/baichuan7B/modeling_baichuan_7B.py
lms/runtime/prune/llm_pruner/LLMPruner/models/hf_bloom/__init__.py
lms/runtime/prune/llm_pruner/LLMPruner/models/hf_bloom/modeling_bloom.py
lms/runtime/prune/llm_pruner/LLMPruner/models/hf_chatglm/__init__.py
lms/runtime/prune/llm_pruner/LLMPruner/models/hf_chatglm/configuration_chatglm.py
lms/runtime/prune/llm_pruner/LLMPruner/models/hf_chatglm/modeling_chatglm.py
lms/runtime/prune/llm_pruner/LLMPruner/models/hf_chatglm/tokenizer_chatglm.py
lms/runtime/prune/llm_pruner/LLMPruner/models/hf_llama/__init__.py
lms/runtime/prune/llm_pruner/LLMPruner/models/hf_llama/modeling_llama.py
lms/runtime/prune/llm_pruner/LLMPruner/models/llama/__init__.py
lms/runtime/prune/llm_pruner/LLMPruner/models/llama/generation.py
lms/runtime/prune/llm_pruner/LLMPruner/models/llama/model.py
lms/runtime/prune/llm_pruner/LLMPruner/models/llama/tokenizer.py
lms/runtime/prune/llm_pruner/LLMPruner/peft/__init__.py
lms/runtime/prune/llm_pruner/LLMPruner/peft/import_utils.py
lms/runtime/prune/llm_pruner/LLMPruner/peft/mapping.py
lms/runtime/prune/llm_pruner/LLMPruner/peft/peft_model.py
lms/runtime/prune/llm_pruner/LLMPruner/peft/tuners/__init__.py
lms/runtime/prune/llm_pruner/LLMPruner/peft/tuners/adalora.py
lms/runtime/prune/llm_pruner/LLMPruner/peft/tuners/lora.py
lms/runtime/prune/llm_pruner/LLMPruner/peft/tuners/p_tuning.py
lms/runtime/prune/llm_pruner/LLMPruner/peft/tuners/prefix_tuning.py
lms/runtime/prune/llm_pruner/LLMPruner/peft/tuners/prompt_tuning.py
lms/runtime/prune/llm_pruner/LLMPruner/peft/utils/__init__.py
lms/runtime/prune/llm_pruner/LLMPruner/peft/utils/config.py
lms/runtime/prune/llm_pruner/LLMPruner/peft/utils/other.py
lms/runtime/prune/llm_pruner/LLMPruner/peft/utils/save_and_load.py
lms/runtime/prune/llm_pruner/LLMPruner/pruner/__init__.py
lms/runtime/prune/llm_pruner/LLMPruner/pruner/hf_baichuan_pruner.py
lms/runtime/prune/llm_pruner/LLMPruner/pruner/hf_chatglm_pruner.py
lms/runtime/prune/llm_pruner/LLMPruner/pruner/hf_llama_pruner.py
lms/runtime/prune/llm_pruner/LLMPruner/pruner/llama_pruner.py
lms/runtime/prune/llm_pruner/LLMPruner/templates/prompts.py
lms/runtime/prune/llm_pruner/LLMPruner/torch_pruning/__init__.py
lms/runtime/prune/llm_pruner/LLMPruner/torch_pruning/_helpers.py
lms/runtime/prune/llm_pruner/LLMPruner/torch_pruning/dependency.py
lms/runtime/prune/llm_pruner/LLMPruner/torch_pruning/importance.py
lms/runtime/prune/llm_pruner/LLMPruner/torch_pruning/ops.py
lms/runtime/prune/llm_pruner/LLMPruner/torch_pruning/pruner/__init__.py
lms/runtime/prune/llm_pruner/LLMPruner/torch_pruning/pruner/function.py
lms/runtime/prune/llm_pruner/LLMPruner/torch_pruning/pruner/algorithms/__init__.py
lms/runtime/prune/llm_pruner/LLMPruner/torch_pruning/pruner/algorithms/batchnorm_scale_pruner.py
lms/runtime/prune/llm_pruner/LLMPruner/torch_pruning/pruner/algorithms/group_norm_pruner.py
lms/runtime/prune/llm_pruner/LLMPruner/torch_pruning/pruner/algorithms/magnitude_based_pruner.py
lms/runtime/prune/llm_pruner/LLMPruner/torch_pruning/pruner/algorithms/metapruner.py
lms/runtime/prune/llm_pruner/LLMPruner/torch_pruning/pruner/algorithms/scheduler.py
lms/runtime/prune/llm_pruner/LLMPruner/torch_pruning/utils/__init__.py
lms/runtime/prune/llm_pruner/LLMPruner/torch_pruning/utils/op_counter.py
lms/runtime/prune/llm_pruner/LLMPruner/torch_pruning/utils/utils.py
lms/runtime/prune/llm_pruner/LLMPruner/utils/logger.py
lms/runtime/prune/llm_pruner/LLMPruner/utils/prompter.py
lms/runtime/prune/sparsegpt/__init__.py
lms/runtime/prune/sparsegpt/entry.py
lms/runtime/prune/sparsegpt/sparsegpt.py
lms/runtime/prune/sparsegpt/test.py
lms/runtime/prune/sparsegpt/util.py
lms/runtime/quantize/__init__.py
lms/runtime/quantize/bnb.py
lms/runtime/quantize/gptq.py
lms/runtime/quantize/util.py
lms/web/__init__.py
lms/web/default_open_sota_model_metrics.json
lms/web/exceptions.py
lms/web/launcher.py
lms/web/main.py
lms/web/route.py
lms/web/internal/__init__.py
lms/web/internal/route.py
lms/web/static/__init__.py
lms/web/static/empty.2f588adb.png
lms/web/static/favicon.png
lms/web/static/index.html
lms/web/static/quickguide.md
lms/web/static/test.md
lms/web/static/umi.css
lms/web/static/umi.js
lms/web/utils/__init__.py
lms/web/utils/asyncssh_utils.py
lms/web/utils/peewee_repo.py
lms/web/utils/traceback_utils.py