Add INCLUDE tasks (#2769)

* Add INCLUDE tasks

* pacify pre-commit

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

lm_eval/tasks/include/few_shot_og/Uzbek/include_base_44_uzbek_arts_humanities.yaml

+include: _uzbek_few_shot_og_template_yaml
+description: Quyida Arts & Humanities boʻyicha koʻp tanlovli savollar (javoblari bilan)
+  keltirilgan.
+process_docs: !function 'utils.process_arts_humanities'
+task: include_base_44_uzbek_few_shot_og_arts_humanities

lm_eval/tasks/include/few_shot_og/Uzbek/include_base_44_uzbek_medical_license.yaml

+include: _uzbek_few_shot_og_template_yaml
+description: Quyida Medical License boʻyicha koʻp tanlovli savollar (javoblari bilan)
+  keltirilgan.
+process_docs: !function 'utils.process_medical_license'
+task: include_base_44_uzbek_few_shot_og_medical_license

lm_eval/tasks/include/few_shot_og/Uzbek/include_base_44_uzbek_social_science.yaml

+include: _uzbek_few_shot_og_template_yaml
+description: Quyida Social Science boʻyicha koʻp tanlovli savollar (javoblari bilan)
+  keltirilgan.
+process_docs: !function 'utils.process_social_science'
+task: include_base_44_uzbek_few_shot_og_social_science

lm_eval/tasks/include/few_shot_og/Uzbek/include_base_44_uzbek_stem.yaml

+include: _uzbek_few_shot_og_template_yaml
+description: Quyida STEM boʻyicha koʻp tanlovli savollar (javoblari bilan) keltirilgan.
+process_docs: !function 'utils.process_stem'
+task: include_base_44_uzbek_few_shot_og_stem

lm_eval/tasks/include/few_shot_og/Uzbek/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/Vietnamese/_include_base_44_vietnamese.yaml

+group: include_base_44_vietnamese
+task:
+- include_base_44_vietnamese_few_shot_og_stem
+- include_base_44_vietnamese_few_shot_og_arts_humanities
+- include_base_44_vietnamese_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/Vietnamese/_vietnamese_few_shot_og_template_yaml

+dataset_path: CohereForAI/include-base-44
+dataset_name: Vietnamese
+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/Vietnamese/include_base_44_vietnamese_arts_humanities.yaml

+include: _vietnamese_few_shot_og_template_yaml
+description: Sau đây là các câu hỏi trắc nghiệm (có đáp án) về Arts & Humanities.
+process_docs: !function 'utils.process_arts_humanities'
+task: include_base_44_vietnamese_few_shot_og_arts_humanities

lm_eval/tasks/include/few_shot_og/Vietnamese/include_base_44_vietnamese_social_science.yaml

+include: _vietnamese_few_shot_og_template_yaml
+description: Sau đây là các câu hỏi trắc nghiệm (có đáp án) về Social Science.
+process_docs: !function 'utils.process_social_science'
+task: include_base_44_vietnamese_few_shot_og_social_science

lm_eval/tasks/include/few_shot_og/Vietnamese/include_base_44_vietnamese_stem.yaml

+include: _vietnamese_few_shot_og_template_yaml
+description: Sau đây là các câu hỏi trắc nghiệm (có đáp án) về STEM.
+process_docs: !function 'utils.process_stem'
+task: include_base_44_vietnamese_few_shot_og_stem

lm_eval/tasks/include/few_shot_og/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)

tests/test_tasks.py

@@ -14,7 +14,7 @@ from .utils import new_tasks
 datasets.config.HF_DATASETS_TRUST_REMOTE_CODE = True
 os.environ["TOKENIZERS_PARALLELISM"] = "false"
 # Default Task
-TASKS = ["arc_easy"]
+TASKS = ["include_base_44_dutch_few_shot_en_applied_science"]
 
 
 def get_new_tasks_else_default():