Merge branch 'smolrefact' into tasklist

# Conflicts:
#	lm_eval/__main__.py
#	lm_eval/api/group.py
#	lm_eval/api/task.py
#	lm_eval/evaluator_utils.py
#	lm_eval/tasks/__init__.py
#	lm_eval/utils.py
#	pyproject.toml

lm_eval/tasks/blimp_nl/passive__ditransitive_2.yaml

+dataset_name: passive__ditransitive_2
+include: _template_yaml
+task: blimp_nl__passive__ditransitive_2

lm_eval/tasks/blimp_nl/passive__impersonal.yaml

+dataset_name: passive__impersonal
+include: _template_yaml
+task: blimp_nl__passive__impersonal

lm_eval/tasks/blimp_nl/quantifiers__universal_difference_agreement_plural.yaml

+dataset_name: quantifiers__universal_difference_agreement_plural
+include: _template_yaml
+task: blimp_nl__quantifiers__universal_difference_agreement_plural

lm_eval/tasks/blimp_nl/quantifiers__universal_difference_agreement_singular.yaml

+dataset_name: quantifiers__universal_difference_agreement_singular
+include: _template_yaml
+task: blimp_nl__quantifiers__universal_difference_agreement_singular

lm_eval/tasks/blimp_nl/r_words__adverbial.yaml

+dataset_name: r_words__adverbial
+include: _template_yaml
+task: blimp_nl__r_words__adverbial

lm_eval/tasks/blimp_nl/r_words__weak_proform.yaml

+dataset_name: r_words__weak_proform
+include: _template_yaml
+task: blimp_nl__r_words__weak_proform

lm_eval/tasks/blimp_nl/relativization__island.yaml

+dataset_name: relativization__island
+include: _template_yaml
+task: blimp_nl__relativization__island

lm_eval/tasks/blimp_nl/relativization__pied_piping.yaml

+dataset_name: relativization__pied_piping
+include: _template_yaml
+task: blimp_nl__relativization__pied_piping

lm_eval/tasks/blimp_nl/relativization__resumptive_prolepsis.yaml

+dataset_name: relativization__resumptive_prolepsis
+include: _template_yaml
+task: blimp_nl__relativization__resumptive_prolepsis

lm_eval/tasks/blimp_nl/topicalization__island.yaml

+dataset_name: topicalization__island
+include: _template_yaml
+task: blimp_nl__topicalization__island

lm_eval/tasks/blimp_nl/topicalization__question_similarity_1.yaml

+dataset_name: topicalization__question_similarity_1
+include: _template_yaml
+task: blimp_nl__topicalization__question_similarity_1

lm_eval/tasks/blimp_nl/topicalization__question_similarity_2.yaml

+dataset_name: topicalization__question_similarity_2
+include: _template_yaml
+task: blimp_nl__topicalization__question_similarity_2

lm_eval/tasks/blimp_nl/topicalization__resumptive_prolepsis.yaml

+dataset_name: topicalization__resumptive_prolepsis
+include: _template_yaml
+task: blimp_nl__topicalization__resumptive_prolepsis

lm_eval/tasks/blimp_nl/verb_second__order_embedded.yaml

+dataset_name: verb_second__order_embedded
+include: _template_yaml
+task: blimp_nl__verb_second__order_embedded

lm_eval/tasks/blimp_nl/verb_second__order_main.yaml

+dataset_name: verb_second__order_main
+include: _template_yaml
+task: blimp_nl__verb_second__order_main

lm_eval/tasks/blimp_nl/wh_movement__filler_effect_gap.yaml

+dataset_name: wh_movement__filler_effect_gap
+include: _template_yaml
+task: blimp_nl__wh_movement__filler_effect_gap

lm_eval/tasks/blimp_nl/wh_movement__filler_effect_no_gap.yaml

+dataset_name: wh_movement__filler_effect_no_gap
+include: _template_yaml
+task: blimp_nl__wh_movement__filler_effect_no_gap

lm_eval/tasks/blimp_nl/wh_movement__hierarchy.yaml

+dataset_name: wh_movement__hierarchy
+include: _template_yaml
+task: blimp_nl__wh_movement__hierarchy

lm_eval/tasks/blimp_nl/wh_movement__question_formation.yaml

+dataset_name: wh_movement__question_formation
+include: _template_yaml
+task: blimp_nl__wh_movement__question_formation

lm_eval/tasks/blimp_nl/wh_movement__stranding_1.yaml

+dataset_name: wh_movement__stranding_1
+include: _template_yaml
+task: blimp_nl__wh_movement__stranding_1