Add INCLUDE tasks (#2769)

* Add INCLUDE tasks

* pacify pre-commit

---------
Co-authored-by: Baber <baber@hey.com>

lm_eval/tasks/include/few_shot_og/Lithuanian/_include_base_44_lithuanian.yaml

+group: include_base_44_lithuanian
+task:
+- include_base_44_lithuanian_few_shot_og_arts_humanities
+- include_base_44_lithuanian_few_shot_og_stem
+- include_base_44_lithuanian_few_shot_og_social_science
+- include_base_44_lithuanian_few_shot_og_business_commerce
+- include_base_44_lithuanian_few_shot_og_professional_certification
+aggregate_metric_list:
+- metric: acc
+  weight_by_size: true
+metadata:
+  version: 0.0

lm_eval/tasks/include/few_shot_og/Lithuanian/_lithuanian_few_shot_og_template_yaml

+dataset_path: CohereForAI/include-base-44
+dataset_name: Lithuanian
+test_split: test
+output_type: multiple_choice
+doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\n
+  D. {{option_d}}\nAnswer:"
+doc_to_choice:
+  - A
+  - B
+  - C
+  - D
+doc_to_target: answer
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 0.0

lm_eval/tasks/include/few_shot_og/Lithuanian/include_base_44_lithuanian_arts_humanities.yaml

+include: _lithuanian_few_shot_og_template_yaml
+description: Toliau pateikiami klausimai su atsakymų variantais (su atsakymais) apie
+  Arts & Humanities.
+process_docs: !function 'utils.process_arts_humanities'
+task: include_base_44_lithuanian_few_shot_og_arts_humanities

lm_eval/tasks/include/few_shot_og/Lithuanian/include_base_44_lithuanian_business_commerce.yaml

+include: _lithuanian_few_shot_og_template_yaml
+description: Toliau pateikiami klausimai su atsakymų variantais (su atsakymais) apie
+  Business & Commerce.
+process_docs: !function 'utils.process_business_commerce'
+task: include_base_44_lithuanian_few_shot_og_business_commerce

lm_eval/tasks/include/few_shot_og/Lithuanian/include_base_44_lithuanian_professional_certification.yaml

+include: _lithuanian_few_shot_og_template_yaml
+description: Toliau pateikiami klausimai su atsakymų variantais (su atsakymais) apie
+  Professional certification.
+process_docs: !function 'utils.process_professional_certification'
+task: include_base_44_lithuanian_few_shot_og_professional_certification

lm_eval/tasks/include/few_shot_og/Lithuanian/include_base_44_lithuanian_social_science.yaml

+include: _lithuanian_few_shot_og_template_yaml
+description: Toliau pateikiami klausimai su atsakymų variantais (su atsakymais) apie
+  Social Science.
+process_docs: !function 'utils.process_social_science'
+task: include_base_44_lithuanian_few_shot_og_social_science

lm_eval/tasks/include/few_shot_og/Lithuanian/include_base_44_lithuanian_stem.yaml

+include: _lithuanian_few_shot_og_template_yaml
+description: Toliau pateikiami klausimai su atsakymų variantais (su atsakymais) apie
+  STEM.
+process_docs: !function 'utils.process_stem'
+task: include_base_44_lithuanian_few_shot_og_stem

lm_eval/tasks/include/few_shot_og/Lithuanian/utils.py

+from functools import partial
+
+
+CATEGORIES = [
+    "Applied Science",
+    "Arts & Humanities",
+    "Business & Commerce",
+    "Driving License",
+    "General knowledge",
+    "Health oriented education",
+    "Marine License",
+    "Medical License",
+    "Professional certification",
+    "STEM",
+    "Social Science",
+]
+
+
+def process_docs(dataset, category):
+    return dataset.filter(lambda x: x["domain"] == category)
+
+
+process_functions = {
+    f"process_{category.lower().replace(' & ', '_').replace(' ', '_')}": partial(
+        process_docs, category=category
+    )
+    for category in CATEGORIES
+}
+
+globals().update(process_functions)

lm_eval/tasks/include/few_shot_og/Malay/_include_base_44_malay.yaml

+group: include_base_44_malay
+task:
+- include_base_44_malay_few_shot_og_social_science
+- include_base_44_malay_few_shot_og_business_commerce
+- include_base_44_malay_few_shot_og_arts_humanities
+aggregate_metric_list:
+- metric: acc
+  weight_by_size: true
+metadata:
+  version: 0.0

lm_eval/tasks/include/few_shot_og/Malay/_malay_few_shot_og_template_yaml

+dataset_path: CohereForAI/include-base-44
+dataset_name: Malay
+test_split: test
+output_type: multiple_choice
+doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\n
+  D. {{option_d}}\nAnswer:"
+doc_to_choice:
+  - A
+  - B
+  - C
+  - D
+doc_to_target: answer
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 0.0

lm_eval/tasks/include/few_shot_og/Malay/include_base_44_malay_arts_humanities.yaml

+include: _malay_few_shot_og_template_yaml
+description: Berikut ialah soalan aneka pilihan (dengan jawapan) tentang Arts & Humanities.
+process_docs: !function 'utils.process_arts_humanities'
+task: include_base_44_malay_few_shot_og_arts_humanities

lm_eval/tasks/include/few_shot_og/Malay/include_base_44_malay_business_commerce.yaml

+include: _malay_few_shot_og_template_yaml
+description: Berikut ialah soalan aneka pilihan (dengan jawapan) tentang Business
+  & Commerce.
+process_docs: !function 'utils.process_business_commerce'
+task: include_base_44_malay_few_shot_og_business_commerce

lm_eval/tasks/include/few_shot_og/Malay/include_base_44_malay_social_science.yaml

+include: _malay_few_shot_og_template_yaml
+description: Berikut ialah soalan aneka pilihan (dengan jawapan) tentang Social Science.
+process_docs: !function 'utils.process_social_science'
+task: include_base_44_malay_few_shot_og_social_science

lm_eval/tasks/include/few_shot_og/Malay/utils.py

+from functools import partial
+
+
+CATEGORIES = [
+    "Applied Science",
+    "Arts & Humanities",
+    "Business & Commerce",
+    "Driving License",
+    "General knowledge",
+    "Health oriented education",
+    "Marine License",
+    "Medical License",
+    "Professional certification",
+    "STEM",
+    "Social Science",
+]
+
+
+def process_docs(dataset, category):
+    return dataset.filter(lambda x: x["domain"] == category)
+
+
+process_functions = {
+    f"process_{category.lower().replace(' & ', '_').replace(' ', '_')}": partial(
+        process_docs, category=category
+    )
+    for category in CATEGORIES
+}
+
+globals().update(process_functions)

lm_eval/tasks/include/few_shot_og/Malayalam/_include_base_44_malayalam.yaml

+group: include_base_44_malayalam
+task:
+- include_base_44_malayalam_few_shot_og_stem
+- include_base_44_malayalam_few_shot_og_marine_license
+- include_base_44_malayalam_few_shot_og_health_oriented_education
+- include_base_44_malayalam_few_shot_og_arts_humanities
+- include_base_44_malayalam_few_shot_og_social_science
+- include_base_44_malayalam_few_shot_og_general_knowledge
+aggregate_metric_list:
+- metric: acc
+  weight_by_size: true
+metadata:
+  version: 0.0

lm_eval/tasks/include/few_shot_og/Malayalam/_malayalam_few_shot_og_template_yaml

+dataset_path: CohereForAI/include-base-44
+dataset_name: Malayalam
+test_split: test
+output_type: multiple_choice
+doc_to_text: "{{question.strip()}}\nA. {{option_a}}\nB. {{option_b}}\nC. {{option_c}}\n
+  D. {{option_d}}\nAnswer:"
+doc_to_choice:
+  - A
+  - B
+  - C
+  - D
+doc_to_target: answer
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 0.0

lm_eval/tasks/include/few_shot_og/Malayalam/include_base_44_malayalam_arts_humanities.yaml

+include: _malayalam_few_shot_og_template_yaml
+description: ഇനിപ്പറയുന്നവ Arts & Humanities നെക്കുറിച്ചുള്ള മൾട്ടിപ്പിൾ ചോയ്‌സ് ചോദ്യങ്ങളാണ്
+  (ഉത്തരങ്ങളോടെ).
+process_docs: !function 'utils.process_arts_humanities'
+task: include_base_44_malayalam_few_shot_og_arts_humanities

lm_eval/tasks/include/few_shot_og/Malayalam/include_base_44_malayalam_general_knowledge.yaml

+include: _malayalam_few_shot_og_template_yaml
+description: ഇനിപ്പറയുന്നവ General knowledge നെക്കുറിച്ചുള്ള മൾട്ടിപ്പിൾ ചോയ്‌സ് ചോദ്യങ്ങളാണ്
+  (ഉത്തരങ്ങളോടെ).
+process_docs: !function 'utils.process_general_knowledge'
+task: include_base_44_malayalam_few_shot_og_general_knowledge

lm_eval/tasks/include/few_shot_og/Malayalam/include_base_44_malayalam_health_oriented_education.yaml

+include: _malayalam_few_shot_og_template_yaml
+description: ഇനിപ്പറയുന്നവ Health oriented education നെക്കുറിച്ചുള്ള മൾട്ടിപ്പിൾ ചോയ്‌സ്
+  ചോദ്യങ്ങളാണ് (ഉത്തരങ്ങളോടെ).
+process_docs: !function 'utils.process_health_oriented_education'
+task: include_base_44_malayalam_few_shot_og_health_oriented_education

lm_eval/tasks/include/few_shot_og/Malayalam/include_base_44_malayalam_marine_license.yaml

+include: _malayalam_few_shot_og_template_yaml
+description: ഇനിപ്പറയുന്നവ Marine License നെക്കുറിച്ചുള്ള മൾട്ടിപ്പിൾ ചോയ്‌സ് ചോദ്യങ്ങളാണ്
+  (ഉത്തരങ്ങളോടെ).
+process_docs: !function 'utils.process_marine_license'
+task: include_base_44_malayalam_few_shot_og_marine_license