├── .gitignore ├── README.md ├── README_EN.md ├── data ├── dev │ ├── agronomy.csv │ ├── anatomy.csv │ ├── ancient_chinese.csv │ ├── arts.csv │ ├── astronomy.csv │ ├── business_ethics.csv │ ├── chinese_civil_service_exam.csv │ ├── chinese_driving_rule.csv │ ├── chinese_food_culture.csv │ ├── chinese_foreign_policy.csv │ ├── chinese_history.csv │ ├── chinese_literature.csv │ ├── chinese_teacher_qualification.csv │ ├── clinical_knowledge.csv │ ├── college_actuarial_science.csv │ ├── college_education.csv │ ├── college_engineering_hydrology.csv │ ├── college_law.csv │ ├── college_mathematics.csv │ ├── college_medical_statistics.csv │ ├── college_medicine.csv │ ├── computer_science.csv │ ├── computer_security.csv │ ├── conceptual_physics.csv │ ├── construction_project_management.csv │ ├── economics.csv │ ├── education.csv │ ├── electrical_engineering.csv │ ├── elementary_chinese.csv │ ├── elementary_commonsense.csv │ ├── elementary_information_and_technology.csv │ ├── elementary_mathematics.csv │ ├── ethnology.csv │ ├── food_science.csv │ ├── genetics.csv │ ├── global_facts.csv │ ├── high_school_biology.csv │ ├── high_school_chemistry.csv │ ├── high_school_geography.csv │ ├── high_school_mathematics.csv │ ├── high_school_physics.csv │ ├── high_school_politics.csv │ ├── human_sexuality.csv │ ├── international_law.csv │ ├── journalism.csv │ ├── jurisprudence.csv │ ├── legal_and_moral_basis.csv │ ├── logical.csv │ ├── machine_learning.csv │ ├── management.csv │ ├── marketing.csv │ ├── marxist_theory.csv │ ├── modern_chinese.csv │ ├── nutrition.csv │ ├── philosophy.csv │ ├── professional_accounting.csv │ ├── professional_law.csv │ ├── professional_medicine.csv │ ├── professional_psychology.csv │ ├── public_relations.csv │ ├── security_study.csv │ ├── sociology.csv │ ├── sports_science.csv │ ├── traditional_chinese_medicine.csv │ ├── virology.csv │ ├── world_history.csv │ └── world_religions.csv └── test │ ├── agronomy.csv │ ├── anatomy.csv │ ├── ancient_chinese.csv │ ├── arts.csv │ ├── astronomy.csv │ ├── business_ethics.csv │ ├── chinese_civil_service_exam.csv │ ├── chinese_driving_rule.csv │ ├── chinese_food_culture.csv │ ├── chinese_foreign_policy.csv │ ├── chinese_history.csv │ ├── chinese_literature.csv │ ├── chinese_teacher_qualification.csv │ ├── clinical_knowledge.csv │ ├── college_actuarial_science.csv │ ├── college_education.csv │ ├── college_engineering_hydrology.csv │ ├── college_law.csv │ ├── college_mathematics.csv │ ├── college_medical_statistics.csv │ ├── college_medicine.csv │ ├── computer_science.csv │ ├── computer_security.csv │ ├── conceptual_physics.csv │ ├── construction_project_management.csv │ ├── economics.csv │ ├── education.csv │ ├── electrical_engineering.csv │ ├── elementary_chinese.csv │ ├── elementary_commonsense.csv │ ├── elementary_information_and_technology.csv │ ├── elementary_mathematics.csv │ ├── ethnology.csv │ ├── food_science.csv │ ├── genetics.csv │ ├── global_facts.csv │ ├── high_school_biology.csv │ ├── high_school_chemistry.csv │ ├── high_school_geography.csv │ ├── high_school_mathematics.csv │ ├── high_school_physics.csv │ ├── high_school_politics.csv │ ├── human_sexuality.csv │ ├── international_law.csv │ ├── journalism.csv │ ├── jurisprudence.csv │ ├── legal_and_moral_basis.csv │ ├── logical.csv │ ├── machine_learning.csv │ ├── management.csv │ ├── marketing.csv │ ├── marxist_theory.csv │ ├── modern_chinese.csv │ ├── nutrition.csv │ ├── philosophy.csv │ ├── professional_accounting.csv │ ├── professional_law.csv │ ├── professional_medicine.csv │ ├── professional_psychology.csv │ ├── public_relations.csv │ ├── security_study.csv │ ├── sociology.csv │ ├── sports_science.csv │ ├── traditional_chinese_medicine.csv │ ├── virology.csv │ ├── world_history.csv │ └── world_religions.csv ├── fig ├── banner.jpg ├── banner_zh.jpg └── logo.jpg ├── script ├── no_slurm_example.sh └── slurm_example.sh └── src ├── batgpt.py ├── categories.py ├── chatglm.py ├── chatgpt.py ├── chinese_llama_alpaca.py ├── ernie.py ├── glm.py ├── gpt4.py ├── hf_causal_model.py ├── lingzhi.py ├── llama3.py ├── moss.py ├── mp_utils.py ├── qwen.py ├── qwen1.5.py ├── qwen2.py ├── run_pci_eval.py └── telechat2.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/README.md -------------------------------------------------------------------------------- /README_EN.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/README_EN.md -------------------------------------------------------------------------------- /data/dev/agronomy.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/agronomy.csv -------------------------------------------------------------------------------- /data/dev/anatomy.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/anatomy.csv -------------------------------------------------------------------------------- /data/dev/ancient_chinese.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/ancient_chinese.csv -------------------------------------------------------------------------------- /data/dev/arts.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/arts.csv -------------------------------------------------------------------------------- /data/dev/astronomy.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/astronomy.csv -------------------------------------------------------------------------------- /data/dev/business_ethics.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/business_ethics.csv -------------------------------------------------------------------------------- /data/dev/chinese_civil_service_exam.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/chinese_civil_service_exam.csv -------------------------------------------------------------------------------- /data/dev/chinese_driving_rule.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/chinese_driving_rule.csv -------------------------------------------------------------------------------- /data/dev/chinese_food_culture.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/chinese_food_culture.csv -------------------------------------------------------------------------------- /data/dev/chinese_foreign_policy.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/chinese_foreign_policy.csv -------------------------------------------------------------------------------- /data/dev/chinese_history.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/chinese_history.csv -------------------------------------------------------------------------------- /data/dev/chinese_literature.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/chinese_literature.csv -------------------------------------------------------------------------------- /data/dev/chinese_teacher_qualification.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/chinese_teacher_qualification.csv -------------------------------------------------------------------------------- /data/dev/clinical_knowledge.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/clinical_knowledge.csv -------------------------------------------------------------------------------- /data/dev/college_actuarial_science.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/college_actuarial_science.csv -------------------------------------------------------------------------------- /data/dev/college_education.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/college_education.csv -------------------------------------------------------------------------------- /data/dev/college_engineering_hydrology.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/college_engineering_hydrology.csv -------------------------------------------------------------------------------- /data/dev/college_law.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/college_law.csv -------------------------------------------------------------------------------- /data/dev/college_mathematics.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/college_mathematics.csv -------------------------------------------------------------------------------- /data/dev/college_medical_statistics.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/college_medical_statistics.csv -------------------------------------------------------------------------------- /data/dev/college_medicine.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/college_medicine.csv -------------------------------------------------------------------------------- /data/dev/computer_science.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/computer_science.csv -------------------------------------------------------------------------------- /data/dev/computer_security.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/computer_security.csv -------------------------------------------------------------------------------- /data/dev/conceptual_physics.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/conceptual_physics.csv -------------------------------------------------------------------------------- /data/dev/construction_project_management.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/construction_project_management.csv -------------------------------------------------------------------------------- /data/dev/economics.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/economics.csv -------------------------------------------------------------------------------- /data/dev/education.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/education.csv -------------------------------------------------------------------------------- /data/dev/electrical_engineering.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/electrical_engineering.csv -------------------------------------------------------------------------------- /data/dev/elementary_chinese.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/elementary_chinese.csv -------------------------------------------------------------------------------- /data/dev/elementary_commonsense.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/elementary_commonsense.csv -------------------------------------------------------------------------------- /data/dev/elementary_information_and_technology.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/elementary_information_and_technology.csv -------------------------------------------------------------------------------- /data/dev/elementary_mathematics.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/elementary_mathematics.csv -------------------------------------------------------------------------------- /data/dev/ethnology.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/ethnology.csv -------------------------------------------------------------------------------- /data/dev/food_science.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/food_science.csv -------------------------------------------------------------------------------- /data/dev/genetics.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/genetics.csv -------------------------------------------------------------------------------- /data/dev/global_facts.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/global_facts.csv -------------------------------------------------------------------------------- /data/dev/high_school_biology.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/high_school_biology.csv -------------------------------------------------------------------------------- /data/dev/high_school_chemistry.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/high_school_chemistry.csv -------------------------------------------------------------------------------- /data/dev/high_school_geography.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/high_school_geography.csv -------------------------------------------------------------------------------- /data/dev/high_school_mathematics.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/high_school_mathematics.csv -------------------------------------------------------------------------------- /data/dev/high_school_physics.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/high_school_physics.csv -------------------------------------------------------------------------------- /data/dev/high_school_politics.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/high_school_politics.csv -------------------------------------------------------------------------------- /data/dev/human_sexuality.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/human_sexuality.csv -------------------------------------------------------------------------------- /data/dev/international_law.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/international_law.csv -------------------------------------------------------------------------------- /data/dev/journalism.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/journalism.csv -------------------------------------------------------------------------------- /data/dev/jurisprudence.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/jurisprudence.csv -------------------------------------------------------------------------------- /data/dev/legal_and_moral_basis.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/legal_and_moral_basis.csv -------------------------------------------------------------------------------- /data/dev/logical.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/logical.csv -------------------------------------------------------------------------------- /data/dev/machine_learning.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/machine_learning.csv -------------------------------------------------------------------------------- /data/dev/management.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/management.csv -------------------------------------------------------------------------------- /data/dev/marketing.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/marketing.csv -------------------------------------------------------------------------------- /data/dev/marxist_theory.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/marxist_theory.csv -------------------------------------------------------------------------------- /data/dev/modern_chinese.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/modern_chinese.csv -------------------------------------------------------------------------------- /data/dev/nutrition.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/nutrition.csv -------------------------------------------------------------------------------- /data/dev/philosophy.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/philosophy.csv -------------------------------------------------------------------------------- /data/dev/professional_accounting.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/professional_accounting.csv -------------------------------------------------------------------------------- /data/dev/professional_law.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/professional_law.csv -------------------------------------------------------------------------------- /data/dev/professional_medicine.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/professional_medicine.csv -------------------------------------------------------------------------------- /data/dev/professional_psychology.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/professional_psychology.csv -------------------------------------------------------------------------------- /data/dev/public_relations.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/public_relations.csv -------------------------------------------------------------------------------- /data/dev/security_study.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/security_study.csv -------------------------------------------------------------------------------- /data/dev/sociology.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/sociology.csv -------------------------------------------------------------------------------- /data/dev/sports_science.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/sports_science.csv -------------------------------------------------------------------------------- /data/dev/traditional_chinese_medicine.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/traditional_chinese_medicine.csv -------------------------------------------------------------------------------- /data/dev/virology.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/virology.csv -------------------------------------------------------------------------------- /data/dev/world_history.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/world_history.csv -------------------------------------------------------------------------------- /data/dev/world_religions.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/dev/world_religions.csv -------------------------------------------------------------------------------- /data/test/agronomy.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/agronomy.csv -------------------------------------------------------------------------------- /data/test/anatomy.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/anatomy.csv -------------------------------------------------------------------------------- /data/test/ancient_chinese.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/ancient_chinese.csv -------------------------------------------------------------------------------- /data/test/arts.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/arts.csv -------------------------------------------------------------------------------- /data/test/astronomy.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/astronomy.csv -------------------------------------------------------------------------------- /data/test/business_ethics.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/business_ethics.csv -------------------------------------------------------------------------------- /data/test/chinese_civil_service_exam.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/chinese_civil_service_exam.csv -------------------------------------------------------------------------------- /data/test/chinese_driving_rule.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/chinese_driving_rule.csv -------------------------------------------------------------------------------- /data/test/chinese_food_culture.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/chinese_food_culture.csv -------------------------------------------------------------------------------- /data/test/chinese_foreign_policy.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/chinese_foreign_policy.csv -------------------------------------------------------------------------------- /data/test/chinese_history.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/chinese_history.csv -------------------------------------------------------------------------------- /data/test/chinese_literature.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/chinese_literature.csv -------------------------------------------------------------------------------- /data/test/chinese_teacher_qualification.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/chinese_teacher_qualification.csv -------------------------------------------------------------------------------- /data/test/clinical_knowledge.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/clinical_knowledge.csv -------------------------------------------------------------------------------- /data/test/college_actuarial_science.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/college_actuarial_science.csv -------------------------------------------------------------------------------- /data/test/college_education.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/college_education.csv -------------------------------------------------------------------------------- /data/test/college_engineering_hydrology.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/college_engineering_hydrology.csv -------------------------------------------------------------------------------- /data/test/college_law.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/college_law.csv -------------------------------------------------------------------------------- /data/test/college_mathematics.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/college_mathematics.csv -------------------------------------------------------------------------------- /data/test/college_medical_statistics.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/college_medical_statistics.csv -------------------------------------------------------------------------------- /data/test/college_medicine.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/college_medicine.csv -------------------------------------------------------------------------------- /data/test/computer_science.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/computer_science.csv -------------------------------------------------------------------------------- /data/test/computer_security.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/computer_security.csv -------------------------------------------------------------------------------- /data/test/conceptual_physics.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/conceptual_physics.csv -------------------------------------------------------------------------------- /data/test/construction_project_management.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/construction_project_management.csv -------------------------------------------------------------------------------- /data/test/economics.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/economics.csv -------------------------------------------------------------------------------- /data/test/education.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/education.csv -------------------------------------------------------------------------------- /data/test/electrical_engineering.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/electrical_engineering.csv -------------------------------------------------------------------------------- /data/test/elementary_chinese.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/elementary_chinese.csv -------------------------------------------------------------------------------- /data/test/elementary_commonsense.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/elementary_commonsense.csv -------------------------------------------------------------------------------- /data/test/elementary_information_and_technology.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/elementary_information_and_technology.csv -------------------------------------------------------------------------------- /data/test/elementary_mathematics.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/elementary_mathematics.csv -------------------------------------------------------------------------------- /data/test/ethnology.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/ethnology.csv -------------------------------------------------------------------------------- /data/test/food_science.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/food_science.csv -------------------------------------------------------------------------------- /data/test/genetics.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/genetics.csv -------------------------------------------------------------------------------- /data/test/global_facts.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/global_facts.csv -------------------------------------------------------------------------------- /data/test/high_school_biology.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/high_school_biology.csv -------------------------------------------------------------------------------- /data/test/high_school_chemistry.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/high_school_chemistry.csv -------------------------------------------------------------------------------- /data/test/high_school_geography.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/high_school_geography.csv -------------------------------------------------------------------------------- /data/test/high_school_mathematics.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/high_school_mathematics.csv -------------------------------------------------------------------------------- /data/test/high_school_physics.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/high_school_physics.csv -------------------------------------------------------------------------------- /data/test/high_school_politics.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/high_school_politics.csv -------------------------------------------------------------------------------- /data/test/human_sexuality.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/human_sexuality.csv -------------------------------------------------------------------------------- /data/test/international_law.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/international_law.csv -------------------------------------------------------------------------------- /data/test/journalism.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/journalism.csv -------------------------------------------------------------------------------- /data/test/jurisprudence.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/jurisprudence.csv -------------------------------------------------------------------------------- /data/test/legal_and_moral_basis.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/legal_and_moral_basis.csv -------------------------------------------------------------------------------- /data/test/logical.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/logical.csv -------------------------------------------------------------------------------- /data/test/machine_learning.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/machine_learning.csv -------------------------------------------------------------------------------- /data/test/management.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/management.csv -------------------------------------------------------------------------------- /data/test/marketing.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/marketing.csv -------------------------------------------------------------------------------- /data/test/marxist_theory.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/marxist_theory.csv -------------------------------------------------------------------------------- /data/test/modern_chinese.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/modern_chinese.csv -------------------------------------------------------------------------------- /data/test/nutrition.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/nutrition.csv -------------------------------------------------------------------------------- /data/test/philosophy.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/philosophy.csv -------------------------------------------------------------------------------- /data/test/professional_accounting.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/professional_accounting.csv -------------------------------------------------------------------------------- /data/test/professional_law.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/professional_law.csv -------------------------------------------------------------------------------- /data/test/professional_medicine.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/professional_medicine.csv -------------------------------------------------------------------------------- /data/test/professional_psychology.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/professional_psychology.csv -------------------------------------------------------------------------------- /data/test/public_relations.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/public_relations.csv -------------------------------------------------------------------------------- /data/test/security_study.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/security_study.csv -------------------------------------------------------------------------------- /data/test/sociology.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/sociology.csv -------------------------------------------------------------------------------- /data/test/sports_science.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/sports_science.csv -------------------------------------------------------------------------------- /data/test/traditional_chinese_medicine.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/traditional_chinese_medicine.csv -------------------------------------------------------------------------------- /data/test/virology.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/virology.csv -------------------------------------------------------------------------------- /data/test/world_history.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/world_history.csv -------------------------------------------------------------------------------- /data/test/world_religions.csv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/data/test/world_religions.csv -------------------------------------------------------------------------------- /fig/banner.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/fig/banner.jpg -------------------------------------------------------------------------------- /fig/banner_zh.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/fig/banner_zh.jpg -------------------------------------------------------------------------------- /fig/logo.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/fig/logo.jpg -------------------------------------------------------------------------------- /script/no_slurm_example.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/script/no_slurm_example.sh -------------------------------------------------------------------------------- /script/slurm_example.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/script/slurm_example.sh -------------------------------------------------------------------------------- /src/batgpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/src/batgpt.py -------------------------------------------------------------------------------- /src/categories.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/src/categories.py -------------------------------------------------------------------------------- /src/chatglm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/src/chatglm.py -------------------------------------------------------------------------------- /src/chatgpt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/src/chatgpt.py -------------------------------------------------------------------------------- /src/chinese_llama_alpaca.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/src/chinese_llama_alpaca.py -------------------------------------------------------------------------------- /src/ernie.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/src/ernie.py -------------------------------------------------------------------------------- /src/glm.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/src/glm.py -------------------------------------------------------------------------------- /src/gpt4.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/src/gpt4.py -------------------------------------------------------------------------------- /src/hf_causal_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/src/hf_causal_model.py -------------------------------------------------------------------------------- /src/lingzhi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/src/lingzhi.py -------------------------------------------------------------------------------- /src/llama3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/src/llama3.py -------------------------------------------------------------------------------- /src/moss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/src/moss.py -------------------------------------------------------------------------------- /src/mp_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/src/mp_utils.py -------------------------------------------------------------------------------- /src/qwen.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/src/qwen.py -------------------------------------------------------------------------------- /src/qwen1.5.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/src/qwen1.5.py -------------------------------------------------------------------------------- /src/qwen2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/src/qwen2.py -------------------------------------------------------------------------------- /src/run_pci_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/src/run_pci_eval.py -------------------------------------------------------------------------------- /src/telechat2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/haonan-li/CMMLU/HEAD/src/telechat2.py --------------------------------------------------------------------------------