Add INCLUDE tasks (#2769)

* Add INCLUDE tasks

* pacify pre-commit

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

lm_eval/tasks/include/few_shot_en/Vietnamese/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/Albanian/_albanian_few_shot_og_template_yaml

+dataset_path: CohereForAI/include-base-44
+dataset_name: Albanian
+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/Albanian/_include_base_44_albanian.yaml

+group: include_base_44_albanian
+task:
+- include_base_44_albanian_few_shot_og_arts_humanities
+- include_base_44_albanian_few_shot_og_stem
+- include_base_44_albanian_few_shot_og_business_commerce
+- include_base_44_albanian_few_shot_og_social_science
+- include_base_44_albanian_few_shot_og_health_oriented_education
+aggregate_metric_list:
+- metric: acc
+  weight_by_size: true
+metadata:
+  version: 0.0

lm_eval/tasks/include/few_shot_og/Albanian/include_base_44_albanian_arts_humanities.yaml

+include: _albanian_few_shot_og_template_yaml
+description: Më poshtë janë pyetjet me zgjedhje të shumëfishta (me përgjigje) rreth
+  Arts & Humanities.
+process_docs: !function 'utils.process_arts_humanities'
+task: include_base_44_albanian_few_shot_og_arts_humanities

lm_eval/tasks/include/few_shot_og/Albanian/include_base_44_albanian_business_commerce.yaml

+include: _albanian_few_shot_og_template_yaml
+description: Më poshtë janë pyetjet me zgjedhje të shumëfishta (me përgjigje) rreth
+  Business & Commerce.
+process_docs: !function 'utils.process_business_commerce'
+task: include_base_44_albanian_few_shot_og_business_commerce

lm_eval/tasks/include/few_shot_og/Albanian/include_base_44_albanian_health_oriented_education.yaml

+include: _albanian_few_shot_og_template_yaml
+description: Më poshtë janë pyetjet me zgjedhje të shumëfishta (me përgjigje) rreth
+  Health oriented education.
+process_docs: !function 'utils.process_health_oriented_education'
+task: include_base_44_albanian_few_shot_og_health_oriented_education

lm_eval/tasks/include/few_shot_og/Albanian/include_base_44_albanian_social_science.yaml

+include: _albanian_few_shot_og_template_yaml
+description: Më poshtë janë pyetjet me zgjedhje të shumëfishta (me përgjigje) rreth
+  Social Science.
+process_docs: !function 'utils.process_social_science'
+task: include_base_44_albanian_few_shot_og_social_science

lm_eval/tasks/include/few_shot_og/Albanian/include_base_44_albanian_stem.yaml

+include: _albanian_few_shot_og_template_yaml
+description: Më poshtë janë pyetjet me zgjedhje të shumëfishta (me përgjigje) rreth
+  STEM.
+process_docs: !function 'utils.process_stem'
+task: include_base_44_albanian_few_shot_og_stem

lm_eval/tasks/include/few_shot_og/Albanian/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/Arabic/_arabic_few_shot_og_template_yaml

+dataset_path: CohereForAI/include-base-44
+dataset_name: Arabic
+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/Arabic/_include_base_44_arabic.yaml

+group: include_base_44_arabic
+task:
+- include_base_44_arabic_few_shot_og_arts_humanities
+- include_base_44_arabic_few_shot_og_stem
+- include_base_44_arabic_few_shot_og_social_science
+- include_base_44_arabic_few_shot_og_driving_license
+- include_base_44_arabic_few_shot_og_general_knowledge
+- include_base_44_arabic_few_shot_og_business_commerce
+aggregate_metric_list:
+- metric: acc
+  weight_by_size: true
+metadata:
+  version: 0.0

lm_eval/tasks/include/few_shot_og/Arabic/include_base_44_arabic_arts_humanities.yaml

+include: _arabic_few_shot_og_template_yaml
+description: فيما يلي أسئلة اختيارية متعددة (مع الإجابات) حول Arts & Humanities.
+process_docs: !function 'utils.process_arts_humanities'
+task: include_base_44_arabic_few_shot_og_arts_humanities

lm_eval/tasks/include/few_shot_og/Arabic/include_base_44_arabic_business_commerce.yaml

+include: _arabic_few_shot_og_template_yaml
+description: فيما يلي أسئلة اختيارية متعددة (مع الإجابات) حول Business & Commerce.
+process_docs: !function 'utils.process_business_commerce'
+task: include_base_44_arabic_few_shot_og_business_commerce

lm_eval/tasks/include/few_shot_og/Arabic/include_base_44_arabic_driving_license.yaml

+include: _arabic_few_shot_og_template_yaml
+description: فيما يلي أسئلة اختيارية متعددة (مع الإجابات) حول Driving License.
+process_docs: !function 'utils.process_driving_license'
+task: include_base_44_arabic_few_shot_og_driving_license

lm_eval/tasks/include/few_shot_og/Arabic/include_base_44_arabic_general_knowledge.yaml

+include: _arabic_few_shot_og_template_yaml
+description: فيما يلي أسئلة اختيارية متعددة (مع الإجابات) حول General knowledge.
+process_docs: !function 'utils.process_general_knowledge'
+task: include_base_44_arabic_few_shot_og_general_knowledge

lm_eval/tasks/include/few_shot_og/Arabic/include_base_44_arabic_social_science.yaml

+include: _arabic_few_shot_og_template_yaml
+description: فيما يلي أسئلة اختيارية متعددة (مع الإجابات) حول Social Science.
+process_docs: !function 'utils.process_social_science'
+task: include_base_44_arabic_few_shot_og_social_science

lm_eval/tasks/include/few_shot_og/Arabic/include_base_44_arabic_stem.yaml

+include: _arabic_few_shot_og_template_yaml
+description: فيما يلي أسئلة اختيارية متعددة (مع الإجابات) حول STEM.
+process_docs: !function 'utils.process_stem'
+task: include_base_44_arabic_few_shot_og_stem

lm_eval/tasks/include/few_shot_og/Arabic/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/Armenian/_armenian_few_shot_og_template_yaml

+dataset_path: CohereForAI/include-base-44
+dataset_name: Armenian
+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/Armenian/_include_base_44_armenian.yaml

+group: include_base_44_armenian
+task:
+- include_base_44_armenian_few_shot_og_driving_license
+- include_base_44_armenian_few_shot_og_social_science
+- include_base_44_armenian_few_shot_og_arts_humanities
+- include_base_44_armenian_few_shot_og_stem
+aggregate_metric_list:
+- metric: acc
+  weight_by_size: true
+metadata:
+  version: 0.0