Merge branch 'main' into prefill

lm_eval/tasks/mmmu/mmmu_accounting.yaml

+task: mmmu_val_accounting
+include: _template_yaml
+task_alias: Accounting
+dataset_name: Accounting

lm_eval/tasks/mmmu/mmmu_agriculture.yaml

+task: mmmu_val_agriculture
+include: _template_yaml
+task_alias: Agriculture
+dataset_name: Agriculture

lm_eval/tasks/mmmu/mmmu_architecture_and_engineering.yaml

+task: mmmu_val_architecture_and_engineering
+include: _template_yaml
+task_alias: Architecture and Engineering
+dataset_name: Architecture_and_Engineering

lm_eval/tasks/mmmu/mmmu_art.yaml

+task: mmmu_val_art
+include: _template_yaml
+task_alias: Art
+dataset_name: Art

lm_eval/tasks/mmmu/mmmu_art_theory.yaml

+task: mmmu_val_art_theory
+include: _template_yaml
+task_alias: Art Theory
+dataset_name: Art_Theory

lm_eval/tasks/mmmu/mmmu_basic_medical_science.yaml

+task: mmmu_val_basic_medical_science
+include: _template_yaml
+task_alias: Basic Medical Science
+dataset_name: Basic_Medical_Science

lm_eval/tasks/mmmu/mmmu_biology.yaml

+task: mmmu_val_biology
+include: _template_yaml
+task_alias: Biology
+dataset_name: Biology

lm_eval/tasks/mmmu/mmmu_chemistry.yaml

+task: mmmu_val_chemistry
+include: _template_yaml
+task_alias: Chemistry
+dataset_name: Chemistry

lm_eval/tasks/mmmu/mmmu_clinical_medicine.yaml

+task: mmmu_val_clinical_medicine
+include: _template_yaml
+task_alias: Clinical Medicine
+dataset_name: Clinical_Medicine

lm_eval/tasks/mmmu/mmmu_computer_science.yaml

+task: mmmu_val_computer_science
+include: _template_yaml
+task_alias: Computer Science
+dataset_name: Computer_Science

lm_eval/tasks/mmmu/mmmu_design.yaml

+task: mmmu_val_design
+include: _template_yaml
+task_alias: Design
+dataset_name: Design

lm_eval/tasks/mmmu/mmmu_diagnostics_and_laboratory_medicine.yaml

+task: mmmu_val_diagnostics_and_laboratory_medicine
+include: _template_yaml
+task_alias: Diagnostics and Laboratory Medicine
+dataset_name: Diagnostics_and_Laboratory_Medicine

lm_eval/tasks/mmmu/mmmu_economics.yaml

+task: mmmu_val_economics
+include: _template_yaml
+task_alias: Economics
+dataset_name: Economics

lm_eval/tasks/mmmu/mmmu_electronics.yaml

+task: mmmu_val_electronics
+include: _template_yaml
+task_alias: Electronics
+dataset_name: Electronics

lm_eval/tasks/mmmu/mmmu_energy_and_power.yaml

+task: mmmu_val_energy_and_power
+include: _template_yaml
+task_alias: Energy and Power
+dataset_name: Energy_and_Power

lm_eval/tasks/mmmu/mmmu_finance.yaml

+task: mmmu_val_finance
+include: _template_yaml
+task_alias: Finance
+dataset_name: Finance

lm_eval/tasks/mmmu/mmmu_geography.yaml

+task: mmmu_val_geography
+include: _template_yaml
+task_alias: Geography
+dataset_name: Geography

lm_eval/tasks/mmmu/mmmu_history.yaml

+task: mmmu_val_history
+include: _template_yaml
+task_alias: History
+dataset_name: History

lm_eval/tasks/mmmu/mmmu_literature.yaml

+task: mmmu_val_literature
+include: _template_yaml
+task_alias: Literature
+dataset_name: Literature

lm_eval/tasks/mmmu/mmmu_manage.yaml

+task: mmmu_val_manage
+include: _template_yaml
+task_alias: Manage
+dataset_name: Manage