TwT-6's picture
Upload 2667 files
256a159 verified
20240305_153409
tabulate format
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
dataset version metric mode llama-7b-hf
------------------------------------------------- --------- -------- ------ -------------
ceval-computer_network - - - -
ceval-operating_system - - - -
ceval-computer_architecture - - - -
ceval-college_programming - - - -
ceval-college_physics - - - -
ceval-college_chemistry - - - -
ceval-advanced_mathematics - - - -
ceval-probability_and_statistics - - - -
ceval-discrete_mathematics - - - -
ceval-electrical_engineer - - - -
ceval-metrology_engineer - - - -
ceval-high_school_mathematics - - - -
ceval-high_school_physics - - - -
ceval-high_school_chemistry - - - -
ceval-high_school_biology - - - -
ceval-middle_school_mathematics - - - -
ceval-middle_school_biology - - - -
ceval-middle_school_physics - - - -
ceval-middle_school_chemistry - - - -
ceval-veterinary_medicine - - - -
ceval-college_economics - - - -
ceval-business_administration - - - -
ceval-marxism - - - -
ceval-mao_zedong_thought - - - -
ceval-education_science - - - -
ceval-teacher_qualification - - - -
ceval-high_school_politics - - - -
ceval-high_school_geography - - - -
ceval-middle_school_politics - - - -
ceval-middle_school_geography - - - -
ceval-modern_chinese_history - - - -
ceval-ideological_and_moral_cultivation - - - -
ceval-logic - - - -
ceval-law - - - -
ceval-chinese_language_and_literature - - - -
ceval-art_studies - - - -
ceval-professional_tour_guide - - - -
ceval-legal_professional - - - -
ceval-high_school_chinese - - - -
ceval-high_school_history - - - -
ceval-middle_school_history - - - -
ceval-civil_servant - - - -
ceval-sports_science - - - -
ceval-plant_protection - - - -
ceval-basic_medicine - - - -
ceval-clinical_medicine - - - -
ceval-urban_and_rural_planner - - - -
ceval-accountant - - - -
ceval-fire_engineer - - - -
ceval-environmental_impact_assessment_engineer - - - -
ceval-tax_accountant - - - -
ceval-physician - - - -
lukaemon_mmlu_college_biology - - - -
lukaemon_mmlu_college_chemistry - - - -
lukaemon_mmlu_college_computer_science - - - -
lukaemon_mmlu_college_mathematics - - - -
lukaemon_mmlu_college_physics - - - -
lukaemon_mmlu_electrical_engineering - - - -
lukaemon_mmlu_astronomy - - - -
lukaemon_mmlu_anatomy - - - -
lukaemon_mmlu_abstract_algebra - - - -
lukaemon_mmlu_machine_learning - - - -
lukaemon_mmlu_clinical_knowledge - - - -
lukaemon_mmlu_global_facts - - - -
lukaemon_mmlu_management - - - -
lukaemon_mmlu_nutrition - - - -
lukaemon_mmlu_marketing - - - -
lukaemon_mmlu_professional_accounting - - - -
lukaemon_mmlu_high_school_geography - - - -
lukaemon_mmlu_international_law - - - -
lukaemon_mmlu_moral_scenarios - - - -
lukaemon_mmlu_computer_security - - - -
lukaemon_mmlu_high_school_microeconomics - - - -
lukaemon_mmlu_professional_law - - - -
lukaemon_mmlu_medical_genetics - - - -
lukaemon_mmlu_professional_psychology - - - -
lukaemon_mmlu_jurisprudence - - - -
lukaemon_mmlu_world_religions - - - -
lukaemon_mmlu_philosophy - - - -
lukaemon_mmlu_virology - - - -
lukaemon_mmlu_high_school_chemistry - - - -
lukaemon_mmlu_public_relations - - - -
lukaemon_mmlu_high_school_macroeconomics - - - -
lukaemon_mmlu_human_sexuality - - - -
lukaemon_mmlu_elementary_mathematics - - - -
lukaemon_mmlu_high_school_physics - - - -
lukaemon_mmlu_high_school_computer_science - - - -
lukaemon_mmlu_high_school_european_history - - - -
lukaemon_mmlu_business_ethics - - - -
lukaemon_mmlu_moral_disputes - - - -
lukaemon_mmlu_high_school_statistics - - - -
lukaemon_mmlu_miscellaneous - - - -
lukaemon_mmlu_formal_logic - - - -
lukaemon_mmlu_high_school_government_and_politics - - - -
lukaemon_mmlu_prehistory - - - -
lukaemon_mmlu_security_studies - - - -
lukaemon_mmlu_high_school_biology - - - -
lukaemon_mmlu_logical_fallacies - - - -
lukaemon_mmlu_high_school_world_history - - - -
lukaemon_mmlu_professional_medicine - - - -
lukaemon_mmlu_high_school_mathematics - - - -
lukaemon_mmlu_college_medicine - - - -
lukaemon_mmlu_high_school_us_history - - - -
lukaemon_mmlu_sociology - - - -
lukaemon_mmlu_econometrics - - - -
lukaemon_mmlu_high_school_psychology - - - -
lukaemon_mmlu_human_aging - - - -
lukaemon_mmlu_us_foreign_policy - - - -
lukaemon_mmlu_conceptual_physics - - - -
$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$
-------------------------------------------------------------------------------------------------------------------------------- THIS IS A DIVIDER --------------------------------------------------------------------------------------------------------------------------------
csv format
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
dataset,version,metric,mode,llama-7b-hf
ceval-computer_network,-,-,-,-
ceval-operating_system,-,-,-,-
ceval-computer_architecture,-,-,-,-
ceval-college_programming,-,-,-,-
ceval-college_physics,-,-,-,-
ceval-college_chemistry,-,-,-,-
ceval-advanced_mathematics,-,-,-,-
ceval-probability_and_statistics,-,-,-,-
ceval-discrete_mathematics,-,-,-,-
ceval-electrical_engineer,-,-,-,-
ceval-metrology_engineer,-,-,-,-
ceval-high_school_mathematics,-,-,-,-
ceval-high_school_physics,-,-,-,-
ceval-high_school_chemistry,-,-,-,-
ceval-high_school_biology,-,-,-,-
ceval-middle_school_mathematics,-,-,-,-
ceval-middle_school_biology,-,-,-,-
ceval-middle_school_physics,-,-,-,-
ceval-middle_school_chemistry,-,-,-,-
ceval-veterinary_medicine,-,-,-,-
ceval-college_economics,-,-,-,-
ceval-business_administration,-,-,-,-
ceval-marxism,-,-,-,-
ceval-mao_zedong_thought,-,-,-,-
ceval-education_science,-,-,-,-
ceval-teacher_qualification,-,-,-,-
ceval-high_school_politics,-,-,-,-
ceval-high_school_geography,-,-,-,-
ceval-middle_school_politics,-,-,-,-
ceval-middle_school_geography,-,-,-,-
ceval-modern_chinese_history,-,-,-,-
ceval-ideological_and_moral_cultivation,-,-,-,-
ceval-logic,-,-,-,-
ceval-law,-,-,-,-
ceval-chinese_language_and_literature,-,-,-,-
ceval-art_studies,-,-,-,-
ceval-professional_tour_guide,-,-,-,-
ceval-legal_professional,-,-,-,-
ceval-high_school_chinese,-,-,-,-
ceval-high_school_history,-,-,-,-
ceval-middle_school_history,-,-,-,-
ceval-civil_servant,-,-,-,-
ceval-sports_science,-,-,-,-
ceval-plant_protection,-,-,-,-
ceval-basic_medicine,-,-,-,-
ceval-clinical_medicine,-,-,-,-
ceval-urban_and_rural_planner,-,-,-,-
ceval-accountant,-,-,-,-
ceval-fire_engineer,-,-,-,-
ceval-environmental_impact_assessment_engineer,-,-,-,-
ceval-tax_accountant,-,-,-,-
ceval-physician,-,-,-,-
lukaemon_mmlu_college_biology,-,-,-,-
lukaemon_mmlu_college_chemistry,-,-,-,-
lukaemon_mmlu_college_computer_science,-,-,-,-
lukaemon_mmlu_college_mathematics,-,-,-,-
lukaemon_mmlu_college_physics,-,-,-,-
lukaemon_mmlu_electrical_engineering,-,-,-,-
lukaemon_mmlu_astronomy,-,-,-,-
lukaemon_mmlu_anatomy,-,-,-,-
lukaemon_mmlu_abstract_algebra,-,-,-,-
lukaemon_mmlu_machine_learning,-,-,-,-
lukaemon_mmlu_clinical_knowledge,-,-,-,-
lukaemon_mmlu_global_facts,-,-,-,-
lukaemon_mmlu_management,-,-,-,-
lukaemon_mmlu_nutrition,-,-,-,-
lukaemon_mmlu_marketing,-,-,-,-
lukaemon_mmlu_professional_accounting,-,-,-,-
lukaemon_mmlu_high_school_geography,-,-,-,-
lukaemon_mmlu_international_law,-,-,-,-
lukaemon_mmlu_moral_scenarios,-,-,-,-
lukaemon_mmlu_computer_security,-,-,-,-
lukaemon_mmlu_high_school_microeconomics,-,-,-,-
lukaemon_mmlu_professional_law,-,-,-,-
lukaemon_mmlu_medical_genetics,-,-,-,-
lukaemon_mmlu_professional_psychology,-,-,-,-
lukaemon_mmlu_jurisprudence,-,-,-,-
lukaemon_mmlu_world_religions,-,-,-,-
lukaemon_mmlu_philosophy,-,-,-,-
lukaemon_mmlu_virology,-,-,-,-
lukaemon_mmlu_high_school_chemistry,-,-,-,-
lukaemon_mmlu_public_relations,-,-,-,-
lukaemon_mmlu_high_school_macroeconomics,-,-,-,-
lukaemon_mmlu_human_sexuality,-,-,-,-
lukaemon_mmlu_elementary_mathematics,-,-,-,-
lukaemon_mmlu_high_school_physics,-,-,-,-
lukaemon_mmlu_high_school_computer_science,-,-,-,-
lukaemon_mmlu_high_school_european_history,-,-,-,-
lukaemon_mmlu_business_ethics,-,-,-,-
lukaemon_mmlu_moral_disputes,-,-,-,-
lukaemon_mmlu_high_school_statistics,-,-,-,-
lukaemon_mmlu_miscellaneous,-,-,-,-
lukaemon_mmlu_formal_logic,-,-,-,-
lukaemon_mmlu_high_school_government_and_politics,-,-,-,-
lukaemon_mmlu_prehistory,-,-,-,-
lukaemon_mmlu_security_studies,-,-,-,-
lukaemon_mmlu_high_school_biology,-,-,-,-
lukaemon_mmlu_logical_fallacies,-,-,-,-
lukaemon_mmlu_high_school_world_history,-,-,-,-
lukaemon_mmlu_professional_medicine,-,-,-,-
lukaemon_mmlu_high_school_mathematics,-,-,-,-
lukaemon_mmlu_college_medicine,-,-,-,-
lukaemon_mmlu_high_school_us_history,-,-,-,-
lukaemon_mmlu_sociology,-,-,-,-
lukaemon_mmlu_econometrics,-,-,-,-
lukaemon_mmlu_high_school_psychology,-,-,-,-
lukaemon_mmlu_human_aging,-,-,-,-
lukaemon_mmlu_us_foreign_policy,-,-,-,-
lukaemon_mmlu_conceptual_physics,-,-,-,-
$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$
-------------------------------------------------------------------------------------------------------------------------------- THIS IS A DIVIDER --------------------------------------------------------------------------------------------------------------------------------
raw format
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-------------------------------
Model: llama-7b-hf
$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$