Add INCLUDE tasks (#2769)

* Add INCLUDE tasks

* pacify pre-commit

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

lm_eval/tasks/include/few_shot_og/Spanish/include_base_44_spanish_stem.yaml

+include: _spanish_few_shot_og_template_yaml
+description: Las siguientes son preguntas de opción múltiple (con respuestas) sobre
+  STEM.
+process_docs: !function 'utils.process_stem'
+task: include_base_44_spanish_few_shot_og_stem

lm_eval/tasks/include/few_shot_og/Spanish/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/Tagalog/_include_base_44_tagalog.yaml

+group: include_base_44_tagalog
+task:
+- include_base_44_tagalog_few_shot_og_arts_humanities
+- include_base_44_tagalog_few_shot_og_driving_license
+aggregate_metric_list:
+- metric: acc
+  weight_by_size: true
+metadata:
+  version: 0.0

lm_eval/tasks/include/few_shot_og/Tagalog/_tagalog_few_shot_og_template_yaml

+dataset_path: CohereForAI/include-base-44
+dataset_name: Tagalog
+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/Tagalog/include_base_44_tagalog_arts_humanities.yaml

+include: _tagalog_few_shot_og_template_yaml
+description: Ang mga sumusunod ay maramihang pagpipiliang tanong (na may mga sagot)
+  tungkol sa Arts & Humanities.
+process_docs: !function 'utils.process_arts_humanities'
+task: include_base_44_tagalog_few_shot_og_arts_humanities

lm_eval/tasks/include/few_shot_og/Tagalog/include_base_44_tagalog_driving_license.yaml

+include: _tagalog_few_shot_og_template_yaml
+description: Ang mga sumusunod ay maramihang pagpipiliang tanong (na may mga sagot)
+  tungkol sa Driving License.
+process_docs: !function 'utils.process_driving_license'
+task: include_base_44_tagalog_few_shot_og_driving_license

lm_eval/tasks/include/few_shot_og/Tagalog/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/Tamil/_include_base_44_tamil.yaml

+group: include_base_44_tamil
+task:
+- include_base_44_tamil_few_shot_og_stem
+- include_base_44_tamil_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/Tamil/_tamil_few_shot_og_template_yaml

+dataset_path: CohereForAI/include-base-44
+dataset_name: Tamil
+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/Tamil/include_base_44_tamil_general_knowledge.yaml

+include: _tamil_few_shot_og_template_yaml
+description: பின்வருபவை General knowledge பற்றிய பல தேர்வு கேள்விகள் (பதில்களுடன்)
+  உள்ளன.
+process_docs: !function 'utils.process_general_knowledge'
+task: include_base_44_tamil_few_shot_og_general_knowledge

lm_eval/tasks/include/few_shot_og/Tamil/include_base_44_tamil_stem.yaml

+include: _tamil_few_shot_og_template_yaml
+description: பின்வருபவை STEM பற்றிய பல தேர்வு கேள்விகள் (பதில்களுடன்) உள்ளன.
+process_docs: !function 'utils.process_stem'
+task: include_base_44_tamil_few_shot_og_stem

lm_eval/tasks/include/few_shot_og/Tamil/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/Telugu/_include_base_44_telugu.yaml

+group: include_base_44_telugu
+task:
+- include_base_44_telugu_few_shot_og_arts_humanities
+- include_base_44_telugu_few_shot_og_applied_science
+- include_base_44_telugu_few_shot_og_stem
+- include_base_44_telugu_few_shot_og_social_science
+aggregate_metric_list:
+- metric: acc
+  weight_by_size: true
+metadata:
+  version: 0.0

lm_eval/tasks/include/few_shot_og/Telugu/_telugu_few_shot_og_template_yaml

+dataset_path: CohereForAI/include-base-44
+dataset_name: Telugu
+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/Telugu/include_base_44_telugu_applied_science.yaml

+include: _telugu_few_shot_og_template_yaml
+description: Applied Science గురించిన బహుళ-ఎంపిక ప్రశ్నలు (సమాధానాలతో) క్రిందివి.
+process_docs: !function 'utils.process_applied_science'
+task: include_base_44_telugu_few_shot_og_applied_science

lm_eval/tasks/include/few_shot_og/Telugu/include_base_44_telugu_arts_humanities.yaml

+include: _telugu_few_shot_og_template_yaml
+description: Arts & Humanities గురించిన బహుళ-ఎంపిక ప్రశ్నలు (సమాధానాలతో) క్రిందివి.
+process_docs: !function 'utils.process_arts_humanities'
+task: include_base_44_telugu_few_shot_og_arts_humanities

lm_eval/tasks/include/few_shot_og/Telugu/include_base_44_telugu_social_science.yaml

+include: _telugu_few_shot_og_template_yaml
+description: Social Science గురించిన బహుళ-ఎంపిక ప్రశ్నలు (సమాధానాలతో) క్రిందివి.
+process_docs: !function 'utils.process_social_science'
+task: include_base_44_telugu_few_shot_og_social_science

lm_eval/tasks/include/few_shot_og/Telugu/include_base_44_telugu_stem.yaml

+include: _telugu_few_shot_og_template_yaml
+description: STEM గురించిన బహుళ-ఎంపిక ప్రశ్నలు (సమాధానాలతో) క్రిందివి.
+process_docs: !function 'utils.process_stem'
+task: include_base_44_telugu_few_shot_og_stem

lm_eval/tasks/include/few_shot_og/Telugu/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/Turkish/_include_base_44_turkish.yaml

+group: include_base_44_turkish
+task:
+- include_base_44_turkish_few_shot_og_business_commerce
+- include_base_44_turkish_few_shot_og_stem
+- include_base_44_turkish_few_shot_og_arts_humanities
+- include_base_44_turkish_few_shot_og_social_science
+aggregate_metric_list:
+- metric: acc
+  weight_by_size: true
+metadata:
+  version: 0.0