Add files using upload-large-folder tool

lm-evaluation-harness/lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_avca_light/arabic_leaderboard_acva_InfluenceFromChina_light.yaml

@@ -0,0 +1,23 @@
+task: arabic_leaderboard_acva_InfluenceFromChina_light
+dataset_path: arcee-globe/ACVA-10percent
+dataset_name: InfluenceFromChina
+output_type: multiple_choice
+training_split: null
+validation_split: validation
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: validation
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm-evaluation-harness/lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_avca_light/arabic_leaderboard_acva_InfluenceFromRome_light.yaml

@@ -0,0 +1,23 @@
+task: arabic_leaderboard_acva_InfluenceFromRome_light
+dataset_path: arcee-globe/ACVA-10percent
+dataset_name: InfluenceFromRome
+output_type: multiple_choice
+training_split: null
+validation_split: validation
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: validation
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm-evaluation-harness/lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_avca_light/arabic_leaderboard_acva_Jordan_light.yaml

@@ -0,0 +1,23 @@
+task: arabic_leaderboard_acva_Jordan_light
+dataset_path: arcee-globe/ACVA-10percent
+dataset_name: Jordan
+output_type: multiple_choice
+training_split: null
+validation_split: validation
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: validation
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm-evaluation-harness/lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_avca_light/arabic_leaderboard_acva_Libya_light.yaml

@@ -0,0 +1,23 @@
+task: arabic_leaderboard_acva_Libya_light
+dataset_path: arcee-globe/ACVA-10percent
+dataset_name: Libya
+output_type: multiple_choice
+training_split: null
+validation_split: validation
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: validation
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm-evaluation-harness/lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_avca_light/arabic_leaderboard_acva_Mauritania_light.yaml

@@ -0,0 +1,23 @@
+task: arabic_leaderboard_acva_Mauritania_light
+dataset_path: arcee-globe/ACVA-10percent
+dataset_name: Mauritania
+output_type: multiple_choice
+training_split: null
+validation_split: validation
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: validation
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm-evaluation-harness/lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_avca_light/arabic_leaderboard_acva_Mesopotamia_civilization_light.yaml

@@ -0,0 +1,23 @@
+task: arabic_leaderboard_acva_Mesopotamia_civilization_light
+dataset_path: arcee-globe/ACVA-10percent
+dataset_name: Mesopotamia_civilization
+output_type: multiple_choice
+training_split: null
+validation_split: validation
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: validation
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm-evaluation-harness/lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_avca_light/arabic_leaderboard_acva_Morocco_light.yaml

@@ -0,0 +1,23 @@
+task: arabic_leaderboard_acva_Morocco_light
+dataset_path: arcee-globe/ACVA-10percent
+dataset_name: Morocco
+output_type: multiple_choice
+training_split: null
+validation_split: validation
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: validation
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm-evaluation-harness/lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_avca_light/arabic_leaderboard_acva_Oman_light.yaml

@@ -0,0 +1,23 @@
+task: arabic_leaderboard_acva_Oman_light
+dataset_path: arcee-globe/ACVA-10percent
+dataset_name: Oman
+output_type: multiple_choice
+training_split: null
+validation_split: validation
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: validation
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm-evaluation-harness/lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_avca_light/arabic_leaderboard_acva_Palestine_light.yaml

@@ -0,0 +1,23 @@
+task: arabic_leaderboard_acva_Palestine_light
+dataset_path: arcee-globe/ACVA-10percent
+dataset_name: Palestine
+output_type: multiple_choice
+training_split: null
+validation_split: validation
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: validation
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm-evaluation-harness/lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_avca_light/arabic_leaderboard_acva_Saudi_Arabia_light.yaml

@@ -0,0 +1,23 @@
+task: arabic_leaderboard_acva_Saudi_Arabia_light
+dataset_path: arcee-globe/ACVA-10percent
+dataset_name: Saudi_Arabia
+output_type: multiple_choice
+training_split: null
+validation_split: validation
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: validation
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm-evaluation-harness/lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_avca_light/arabic_leaderboard_acva_Sudan_light.yaml

@@ -0,0 +1,23 @@
+task: arabic_leaderboard_acva_Sudan_light
+dataset_path: arcee-globe/ACVA-10percent
+dataset_name: Sudan
+output_type: multiple_choice
+training_split: null
+validation_split: validation
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: validation
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm-evaluation-harness/lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_avca_light/arabic_leaderboard_acva_Syria_light.yaml

@@ -0,0 +1,23 @@
+task: arabic_leaderboard_acva_Syria_light
+dataset_path: arcee-globe/ACVA-10percent
+dataset_name: Syria
+output_type: multiple_choice
+training_split: null
+validation_split: validation
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: validation
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm-evaluation-harness/lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_avca_light/arabic_leaderboard_acva_Tunisia_light.yaml

@@ -0,0 +1,23 @@
+task: arabic_leaderboard_acva_Tunisia_light
+dataset_path: arcee-globe/ACVA-10percent
+dataset_name: Tunisia
+output_type: multiple_choice
+training_split: null
+validation_split: validation
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: validation
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm-evaluation-harness/lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_avca_light/arabic_leaderboard_acva_United_Arab_Emirates_light.yaml

@@ -0,0 +1,23 @@
+task: arabic_leaderboard_acva_United_Arab_Emirates_light
+dataset_path: arcee-globe/ACVA-10percent
+dataset_name: United_Arab_Emirates
+output_type: multiple_choice
+training_split: null
+validation_split: validation
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: validation
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm-evaluation-harness/lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_avca_light/arabic_leaderboard_acva_Yemen_light.yaml

@@ -0,0 +1,23 @@
+task: arabic_leaderboard_acva_Yemen_light
+dataset_path: OALL/ACVA
+dataset_name: Yemen
+output_type: multiple_choice
+training_split: null
+validation_split: validation
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: validation
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm-evaluation-harness/lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_avca_light/arabic_leaderboard_acva_communication_light.yaml

@@ -0,0 +1,23 @@
+task: arabic_leaderboard_acva_communication_light
+dataset_path: arcee-globe/ACVA-10percent
+dataset_name: communication
+output_type: multiple_choice
+training_split: null
+validation_split: validation
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: validation
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm-evaluation-harness/lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_avca_light/arabic_leaderboard_acva_computer_and_phone_light.yaml

@@ -0,0 +1,23 @@
+task: arabic_leaderboard_acva_computer_and_phone_light
+dataset_path: arcee-globe/ACVA-10percent
+dataset_name: computer_and_phone
+output_type: multiple_choice
+training_split: null
+validation_split: validation
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: validation
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm-evaluation-harness/lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_avca_light/arabic_leaderboard_acva_daily_life_light.yaml

@@ -0,0 +1,23 @@
+task: arabic_leaderboard_acva_daily_life_light
+dataset_path: arcee-globe/ACVA-10percent
+dataset_name: daily_life
+output_type: multiple_choice
+training_split: null
+validation_split: validation
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: validation
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm-evaluation-harness/lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_avca_light/arabic_leaderboard_acva_entertainment_light.yaml

@@ -0,0 +1,23 @@
+task: arabic_leaderboard_acva_entertainment_light
+dataset_path: arcee-globe/ACVA-10percent
+dataset_name: entertainment
+output_type: multiple_choice
+training_split: null
+validation_split: validation
+test_split: test
+process_docs: !function utils.process_docs
+doc_to_text: "{{query}}"
+doc_to_target: "{{gold}}"
+doc_to_choice: "choices"
+fewshot_split: validation
+fewshot_config:
+  sampler: first_n
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+  - metric: acc_norm
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm-evaluation-harness/lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_avca_light/arabic_leaderboard_acva_light.yaml

@@ -0,0 +1,70 @@
+group: arabic_leaderboard_acva_light
+task:
+  - arabic_leaderboard_acva_Algeria_light
+  - arabic_leaderboard_acva_Ancient_Egypt_light
+  - arabic_leaderboard_acva_Arab_Empire_light
+  - arabic_leaderboard_acva_Arabic_Architecture_light
+  - arabic_leaderboard_acva_Arabic_Art_light
+  - arabic_leaderboard_acva_Arabic_Astronomy_light
+  - arabic_leaderboard_acva_Arabic_Calligraphy_light
+  - arabic_leaderboard_acva_Arabic_Ceremony_light
+  - arabic_leaderboard_acva_Arabic_Clothing_light
+  - arabic_leaderboard_acva_Arabic_Culture_light
+  - arabic_leaderboard_acva_Arabic_Food_light
+  - arabic_leaderboard_acva_Arabic_Funeral_light
+  - arabic_leaderboard_acva_Arabic_Geography_light
+  - arabic_leaderboard_acva_Arabic_History_light
+  - arabic_leaderboard_acva_Arabic_Language_Origin_light
+  - arabic_leaderboard_acva_Arabic_Literature_light
+  - arabic_leaderboard_acva_Arabic_Math_light
+  - arabic_leaderboard_acva_Arabic_Medicine_light
+  - arabic_leaderboard_acva_Arabic_Music_light
+  - arabic_leaderboard_acva_Arabic_Ornament_light
+  - arabic_leaderboard_acva_Arabic_Philosophy_light
+  - arabic_leaderboard_acva_Arabic_Physics_and_Chemistry_light
+  - arabic_leaderboard_acva_Arabic_Wedding_light
+  - arabic_leaderboard_acva_Bahrain_light
+  - arabic_leaderboard_acva_Comoros_light
+  - arabic_leaderboard_acva_Egypt_modern_light
+  - arabic_leaderboard_acva_InfluenceFromAncientEgypt_light
+  - arabic_leaderboard_acva_InfluenceFromByzantium_light
+  - arabic_leaderboard_acva_InfluenceFromChina_light
+  - arabic_leaderboard_acva_InfluenceFromGreece_light
+  - arabic_leaderboard_acva_InfluenceFromIslam_light
+  - arabic_leaderboard_acva_InfluenceFromPersia_light
+  - arabic_leaderboard_acva_InfluenceFromRome_light
+  - arabic_leaderboard_acva_Iraq_light
+  - arabic_leaderboard_acva_Islam_Education_light
+  - arabic_leaderboard_acva_Islam_branches_and_schools_light
+  - arabic_leaderboard_acva_Islamic_law_system_light
+  - arabic_leaderboard_acva_Jordan_light
+  - arabic_leaderboard_acva_Kuwait_light
+  - arabic_leaderboard_acva_Lebanon_light
+  - arabic_leaderboard_acva_Libya_light
+  - arabic_leaderboard_acva_Mauritania_light
+  - arabic_leaderboard_acva_Mesopotamia_civilization_light
+  - arabic_leaderboard_acva_Morocco_light
+  - arabic_leaderboard_acva_Oman_light
+  - arabic_leaderboard_acva_Palestine_light
+  - arabic_leaderboard_acva_Qatar_light
+  - arabic_leaderboard_acva_Saudi_Arabia_light
+  - arabic_leaderboard_acva_Somalia_light
+  - arabic_leaderboard_acva_Sudan_light
+  - arabic_leaderboard_acva_Syria_light
+  - arabic_leaderboard_acva_Tunisia_light
+  - arabic_leaderboard_acva_United_Arab_Emirates_light
+  - arabic_leaderboard_acva_Yemen_light
+  - arabic_leaderboard_acva_communication_light
+  - arabic_leaderboard_acva_computer_and_phone_light
+  - arabic_leaderboard_acva_daily_life_light
+  - arabic_leaderboard_acva_entertainment_light
+
+aggregate_metric_list:
+  - metric: acc
+    aggregation: mean
+    weight_by_size: true
+  - metric: acc_norm
+    aggregation: mean
+    weight_by_size: true
+metadata:
+  version: 1.0

lm-evaluation-harness/lm_eval/tasks/arabic_leaderboard_light/arabic_leaderboard_avca_light/utils.py

@@ -0,0 +1,16 @@
+import datasets
+import numpy as np
+
+
+def process_docs(dataset: datasets.Dataset):
+    def _process_doc(doc):
+        question = doc["question"]
+        answer = doc["answer"]
+
+        return {
+            "query": f"السؤال: {question}\nالإجابة:",
+            "choices": ["صح", "خطأ"],
+            "gold": ["صح", "خطأ"].index(answer),
+        }
+
+    return dataset.map(_process_doc)

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/_arabicmmlu_social_science.yaml

@@ -0,0 +1,9 @@
+group: arabicmmlu_social_science
+group_alias: Social Science
+task:
+  - arabicmmlu_social_science_tasks
+aggregate_metric_list:
+  - metric: acc
+    weight_by_size: True
+metadata:
+  version: 1

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/_arabicmmlu_stem.yaml

@@ -0,0 +1,9 @@
+group: arabicmmlu_stem
+group_alias: STEM
+task:
+  - arabicmmlu_stem_tasks
+aggregate_metric_list:
+  - metric: acc
+    weight_by_size: True
+metadata:
+  version: 1

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/_default_arabicmmlu_template_yaml

@@ -0,0 +1,15 @@
+dataset_path: MBZUAI/ArabicMMLU
+test_split: test
+fewshot_split: dev
+fewshot_config:
+  sampler: first_n
+output_type: multiple_choice
+doc_to_text: !function utils.doc_to_text
+doc_to_choice: !function utils.doc_to_choice
+doc_to_target: "Answer Key"
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 1.0

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_arabic_language_grammar.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "Arabic Language (Grammar)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_language_tasks"
+"task": "arabicmmlu_arabic_language_grammar"
+"task_alias": "Arabic Language (Grammar)"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_arabic_language_primary_school.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "Arabic Language (Primary School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_language_tasks"
+"task": "arabicmmlu_arabic_language_primary_school"
+"task_alias": "Arabic Language (Primary School)"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_biology_high_school.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "Biology (High School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_stem_tasks"
+"task": "arabicmmlu_biology_high_school"
+"task_alias": "Biology (High School)"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_civics_high_school.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "Civics (High School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_social_science_tasks"
+"task": "arabicmmlu_civics_high_school"
+"task_alias": "Civics (High School)"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_civics_middle_school.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "Civics (Middle School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_social_science_tasks"
+"task": "arabicmmlu_civics_middle_school"
+"task_alias": "Civics (Middle School)"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_computer_science_middle_school.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "Computer Science (Middle School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_stem_tasks"
+"task": "arabicmmlu_computer_science_middle_school"
+"task_alias": "Computer Science (Middle School)"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_computer_science_primary_school.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "Computer Science (Primary School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_stem_tasks"
+"task": "arabicmmlu_computer_science_primary_school"
+"task_alias": "Computer Science (Primary School)"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_computer_science_university.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "Computer Science (University)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_stem_tasks"
+"task": "arabicmmlu_computer_science_university"
+"task_alias": "Computer Science (University)"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_driving_test.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "Driving Test"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_other_tasks"
+"task": "arabicmmlu_driving_test"
+"task_alias": "Driving Test"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_economics_high_school.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "Economics (High School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_social_science_tasks"
+"task": "arabicmmlu_economics_high_school"
+"task_alias": "Economics (High School)"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_economics_middle_school.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "Economics (Middle School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_social_science_tasks"
+"task": "arabicmmlu_economics_middle_school"
+"task_alias": "Economics (Middle School)"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_economics_university.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "Economics (University)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_social_science_tasks"
+"task": "arabicmmlu_economics_university"
+"task_alias": "Economics (University)"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_general_knowledge.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "General Knowledge"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_other_tasks"
+"task": "arabicmmlu_general_knowledge"
+"task_alias": "General Knowledge"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_general_knowledge_middle_school.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "General Knowledge (Middle School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_other_tasks"
+"task": "arabicmmlu_general_knowledge_middle_school"
+"task_alias": "General Knowledge (Middle School)"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_general_knowledge_primary_school.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "General Knowledge (Primary School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_other_tasks"
+"task": "arabicmmlu_general_knowledge_primary_school"
+"task_alias": "General Knowledge (Primary School)"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_geography_high_school.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "Geography (High School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_social_science_tasks"
+"task": "arabicmmlu_geography_high_school"
+"task_alias": "Geography (High School)"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_geography_middle_school.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "Geography (Middle School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_social_science_tasks"
+"task": "arabicmmlu_geography_middle_school"
+"task_alias": "Geography (Middle School)"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_geography_primary_school.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "Geography (Primary School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_social_science_tasks"
+"task": "arabicmmlu_geography_primary_school"
+"task_alias": "Geography (Primary School)"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_history_high_school.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "History (High School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_humanities_tasks"
+"task": "arabicmmlu_history_high_school"
+"task_alias": "History (High School)"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_history_middle_school.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "History (Middle School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_humanities_tasks"
+"task": "arabicmmlu_history_middle_school"
+"task_alias": "History (Middle School)"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_history_primary_school.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "History (Primary School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_humanities_tasks"
+"task": "arabicmmlu_history_primary_school"
+"task_alias": "History (Primary School)"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_islamic_studies_high_school.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "Islamic Studies (High School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_humanities_tasks"
+"task": "arabicmmlu_islamic_studies_high_school"
+"task_alias": "Islamic Studies (High School)"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_islamic_studies_primary_school.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "Islamic Studies (Primary School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_humanities_tasks"
+"task": "arabicmmlu_islamic_studies_primary_school"
+"task_alias": "Islamic Studies (Primary School)"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_law_professional.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "Law (Professional)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_humanities_tasks"
+"task": "arabicmmlu_law_professional"
+"task_alias": "Law (Professional)"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_management_university.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "Management (University)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_other_tasks"
+"task": "arabicmmlu_management_university"
+"task_alias": "Management (University)"

lm-evaluation-harness/lm_eval/tasks/arabicmmlu/arabicmmlu_math_primary_school.yaml

@@ -0,0 +1,5 @@
+"dataset_name": "Math (Primary School)"
+"include": "_default_arabicmmlu_template_yaml"
+"tag": "arabicmmlu_stem_tasks"
+"task": "arabicmmlu_math_primary_school"
+"task_alias": "Math (Primary School)"