Merge pull request #1089 from h-albert-lee/K-MMLU

Add kmmlu evaluation to tasks

lm_eval/tasks/kmmlu/kmmlu_food_processing.yaml

+"dataset_name": "Food Processing"
+"include": "_default_kmmlu_yaml"
+"task": "kmmlu_food_processing"

lm_eval/tasks/kmmlu/kmmlu_gas_technology_and_engineering.yaml

+"dataset_name": "Gas Technology and Engineering"
+"include": "_default_kmmlu_yaml"
+"task": "kmmlu_gas_technology_and_engineering"

lm_eval/tasks/kmmlu/kmmlu_general_physics.yaml

+"dataset_name": "General Physics"
+"include": "_default_kmmlu_yaml"
+"task": "kmmlu_general_physics"

lm_eval/tasks/kmmlu/kmmlu_geomatics.yaml

+"dataset_name": "Geomatics"
+"include": "_default_kmmlu_yaml"
+"task": "kmmlu_geomatics"

lm_eval/tasks/kmmlu/kmmlu_health.yaml

+"dataset_name": "Health"
+"include": "_default_kmmlu_yaml"
+"task": "kmmlu_health"

lm_eval/tasks/kmmlu/kmmlu_industrial_engineer.yaml

+"dataset_name": "Industrial Engineer"
+"include": "_default_kmmlu_yaml"
+"task": "kmmlu_industrial_engineer"

lm_eval/tasks/kmmlu/kmmlu_information_technology.yaml

+"dataset_name": "Information Technology"
+"include": "_default_kmmlu_yaml"
+"task": "kmmlu_information_technology"

lm_eval/tasks/kmmlu/kmmlu_interior_architecture_and_design.yaml

+"dataset_name": "Interior Architecture and Design"
+"include": "_default_kmmlu_yaml"
+"task": "kmmlu_interior_architecture_and_design"

lm_eval/tasks/kmmlu/kmmlu_korean_language.yaml

+"dataset_name": "Korean Language"
+"include": "_default_kmmlu_yaml"
+"task": "kmmlu_korean_language"

lm_eval/tasks/kmmlu/kmmlu_law.yaml

+"dataset_name": "Law"
+"include": "_default_kmmlu_yaml"
+"task": "kmmlu_law"

lm_eval/tasks/kmmlu/kmmlu_machine_design_and_manufacturing.yaml

+"dataset_name": "Machine Design and Manufacturing"
+"include": "_default_kmmlu_yaml"
+"task": "kmmlu_machine_design_and_manufacturing"

lm_eval/tasks/kmmlu/kmmlu_management.yaml

+"dataset_name": "Management"
+"include": "_default_kmmlu_yaml"
+"task": "kmmlu_management"

lm_eval/tasks/kmmlu/kmmlu_maritime_engineering.yaml

+"dataset_name": "Maritime Engineering"
+"include": "_default_kmmlu_yaml"
+"task": "kmmlu_maritime_engineering"

lm_eval/tasks/kmmlu/kmmlu_marketing.yaml

+"dataset_name": "Marketing"
+"include": "_default_kmmlu_yaml"
+"task": "kmmlu_marketing"

lm_eval/tasks/kmmlu/kmmlu_materials_engineering.yaml

+"dataset_name": "Materials Engineering"
+"include": "_default_kmmlu_yaml"
+"task": "kmmlu_materials_engineering"

lm_eval/tasks/kmmlu/kmmlu_mechanical_engineering.yaml

+"dataset_name": "Mechanical Engineering"
+"include": "_default_kmmlu_yaml"
+"task": "kmmlu_mechanical_engineering"

lm_eval/tasks/kmmlu/kmmlu_nondestructive_testing.yaml

+"dataset_name": "Nondestructive Testing"
+"include": "_default_kmmlu_yaml"
+"task": "kmmlu_nondestructive_testing"

lm_eval/tasks/kmmlu/kmmlu_patent.yaml

+"dataset_name": "Patent"
+"include": "_default_kmmlu_yaml"
+"task": "kmmlu_patent"

lm_eval/tasks/kmmlu/kmmlu_political_science_and_sociology.yaml

+"dataset_name": "Political Science and Sociology"
+"include": "_default_kmmlu_yaml"
+"task": "kmmlu_political_science_and_sociology"

lm_eval/tasks/kmmlu/kmmlu_psychology.yaml

+"dataset_name": "Psychology"
+"include": "_default_kmmlu_yaml"
+"task": "kmmlu_psychology"