Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_anatomy.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_ancient_chinese.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_astronomy.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_business_ethics.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_chinese_civil_service_exam.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_chinese_driving_rule.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_chinese_foreign_policy.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_chinese_history.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_chinese_literature.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_chinese_teacher_qualification.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_clinical_knowledge.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_college_education.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_college_law.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_college_medicine.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_construction_project_management.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_agronomy.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_ancient_chinese.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_chinese_driving_rule.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_chinese_food_culture.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_chinese_history.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_chinese_literature.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_clinical_knowledge.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_college_actuarial_science.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_college_engineering_hydrology.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_college_law.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_college_mathematics.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_college_medical_statistics.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_college_medicine.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_conceptual_physics.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_education.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_electrical_engineering.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_elementary_commonsense.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_food_science.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_global_facts.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_high_school_biology.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_high_school_chemistry.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_high_school_mathematics.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_high_school_physics.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_high_school_politics.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_human_sexuality.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_international_law.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_journalism.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_logical.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_machine_learning.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_management.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_marketing.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_nutrition.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_professional_accounting.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_professional_law.yaml +4 -0
- scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_public_relations.yaml +4 -0
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_anatomy.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "anatomy"
|
| 2 |
+
"description": "以下是关于解剖学的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_anatomy"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_ancient_chinese.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "ancient_chinese"
|
| 2 |
+
"description": "以下是关于古汉语的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_ancient_chinese"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_astronomy.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "astronomy"
|
| 2 |
+
"description": "以下是关于天文学的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_astronomy"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_business_ethics.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "business_ethics"
|
| 2 |
+
"description": "以下是关于商业伦理的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_business_ethics"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_chinese_civil_service_exam.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "chinese_civil_service_exam"
|
| 2 |
+
"description": "以下是关于中国公务员考试的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_chinese_civil_service_exam"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_chinese_driving_rule.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "chinese_driving_rule"
|
| 2 |
+
"description": "以下是关于中国驾驶规则的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_chinese_driving_rule"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_chinese_foreign_policy.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "chinese_foreign_policy"
|
| 2 |
+
"description": "以下是关于中国外交政策的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_chinese_foreign_policy"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_chinese_history.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "chinese_history"
|
| 2 |
+
"description": "以下是关于中国历史的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_chinese_history"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_chinese_literature.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "chinese_literature"
|
| 2 |
+
"description": "以下是关于中国文学的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_chinese_literature"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_chinese_teacher_qualification.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "chinese_teacher_qualification"
|
| 2 |
+
"description": "以下是关于中国教师资格的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_chinese_teacher_qualification"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_clinical_knowledge.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "clinical_knowledge"
|
| 2 |
+
"description": "以下是关于临床知识的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_clinical_knowledge"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_college_education.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "college_education"
|
| 2 |
+
"description": "以下是关于大学教育学的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_college_education"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_college_law.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "college_law"
|
| 2 |
+
"description": "以下是关于大学法律的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_college_law"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_college_medicine.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "college_medicine"
|
| 2 |
+
"description": "以下是关于大学医学的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_college_medicine"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_construction_project_management.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "construction_project_management"
|
| 2 |
+
"description": "以下是关于建设工程管理的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_construction_project_management"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_agronomy.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "agronomy"
|
| 2 |
+
"description": "以下是关于农学的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_agronomy"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_ancient_chinese.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "ancient_chinese"
|
| 2 |
+
"description": "以下是关于古汉语的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_ancient_chinese"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_chinese_driving_rule.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "chinese_driving_rule"
|
| 2 |
+
"description": "以下是关于中国驾驶规则的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_chinese_driving_rule"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_chinese_food_culture.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "chinese_food_culture"
|
| 2 |
+
"description": "以下是关于中国饮食文化的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_chinese_food_culture"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_chinese_history.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "chinese_history"
|
| 2 |
+
"description": "以下是关于中国历史的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_chinese_history"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_chinese_literature.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "chinese_literature"
|
| 2 |
+
"description": "以下是关于中国文学的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_chinese_literature"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_clinical_knowledge.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "clinical_knowledge"
|
| 2 |
+
"description": "以下是关于临床知识的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_clinical_knowledge"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_college_actuarial_science.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "college_actuarial_science"
|
| 2 |
+
"description": "以下是关于大学精算学的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_college_actuarial_science"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_college_engineering_hydrology.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "college_engineering_hydrology"
|
| 2 |
+
"description": "以下是关于大学工程水文学的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_college_engineering_hydrology"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_college_law.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "college_law"
|
| 2 |
+
"description": "以下是关于大学法律的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_college_law"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_college_mathematics.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "college_mathematics"
|
| 2 |
+
"description": "以下是关于大学数学的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_college_mathematics"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_college_medical_statistics.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "college_medical_statistics"
|
| 2 |
+
"description": "以下是关于大学医学统计的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_college_medical_statistics"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_college_medicine.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "college_medicine"
|
| 2 |
+
"description": "以下是关于大学医学的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_college_medicine"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_conceptual_physics.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "conceptual_physics"
|
| 2 |
+
"description": "以下是关于概念物理学的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_conceptual_physics"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_education.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "education"
|
| 2 |
+
"description": "以下是关于教育学的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_education"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_electrical_engineering.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "electrical_engineering"
|
| 2 |
+
"description": "以下是关于电气工程的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_electrical_engineering"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_elementary_commonsense.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "elementary_commonsense"
|
| 2 |
+
"description": "以下是关于小学常识的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_elementary_commonsense"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_food_science.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "food_science"
|
| 2 |
+
"description": "以下是关于食品科学的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_food_science"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_global_facts.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "global_facts"
|
| 2 |
+
"description": "以下是关于全球事实的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_global_facts"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_high_school_biology.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "high_school_biology"
|
| 2 |
+
"description": "以下是关于高中生物的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_high_school_biology"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_high_school_chemistry.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "high_school_chemistry"
|
| 2 |
+
"description": "以下是关于高中化学的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_high_school_chemistry"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_high_school_mathematics.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "high_school_mathematics"
|
| 2 |
+
"description": "以下是关于高中数学的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_high_school_mathematics"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_high_school_physics.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "high_school_physics"
|
| 2 |
+
"description": "以下是关于高中物理学的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_high_school_physics"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_high_school_politics.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "high_school_politics"
|
| 2 |
+
"description": "以下是关于高中政治的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_high_school_politics"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_human_sexuality.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "human_sexuality"
|
| 2 |
+
"description": "以下是关于人类性行为的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_human_sexuality"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_international_law.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "international_law"
|
| 2 |
+
"description": "以下是关于国际法学的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_international_law"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_journalism.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "journalism"
|
| 2 |
+
"description": "以下是关于新闻学的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_journalism"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_logical.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "logical"
|
| 2 |
+
"description": "以下是关于逻辑学的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_logical"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_machine_learning.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "machine_learning"
|
| 2 |
+
"description": "以下是关于机器学习的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_machine_learning"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_management.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "management"
|
| 2 |
+
"description": "以下是关于管理学的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_management"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_marketing.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "marketing"
|
| 2 |
+
"description": "以下是关于市场营销的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_marketing"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_nutrition.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "nutrition"
|
| 2 |
+
"description": "以下是关于营养学的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_nutrition"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_professional_accounting.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "professional_accounting"
|
| 2 |
+
"description": "以下是关于专业会计的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_professional_accounting"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_professional_law.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "professional_law"
|
| 2 |
+
"description": "以下是关于专业法学的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_professional_law"
|
scripts/yans/lm-evaluation-harness/lm_eval/tasks/cmmlu/cmmlu_default_public_relations.yaml
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"dataset_name": "public_relations"
|
| 2 |
+
"description": "以下是关于公共关系的单项选择题,请直接给出正确答案的选项。\n\n"
|
| 3 |
+
"include": "_default_template_yaml"
|
| 4 |
+
"task": "cmmlu_public_relations"
|