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

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
abd17276 · Baber · 00afd536 · 70314843 · abd17276 · abd17276
Commit abd17276 authored Sep 26, 2025 by Baber
20 changed files
--- a/lm_eval/tasks/blimp_nl/README.md
+++ b/lm_eval/tasks/blimp_nl/README.md
--- a/lm_eval/tasks/blimp_nl/_template_yaml
+++ b/lm_eval/tasks/blimp_nl/_template_yaml
--- a/lm_eval/tasks/blimp_nl/adpositional_phrases__argument_r_extraction.yaml
+++ b/lm_eval/tasks/blimp_nl/adpositional_phrases__argument_r_extraction.yaml
--- a/lm_eval/tasks/blimp_nl/adpositional_phrases__argument_scrambling.yaml
+++ b/lm_eval/tasks/blimp_nl/adpositional_phrases__argument_scrambling.yaml
--- a/lm_eval/tasks/blimp_nl/adverbial_modification__position_proform.yaml
+++ b/lm_eval/tasks/blimp_nl/adverbial_modification__position_proform.yaml
--- a/lm_eval/tasks/blimp_nl/adverbial_modification__position_type.yaml
+++ b/lm_eval/tasks/blimp_nl/adverbial_modification__position_type.yaml
--- a/lm_eval/tasks/blimp_nl/anaphor_agreement__number.yaml
+++ b/lm_eval/tasks/blimp_nl/anaphor_agreement__number.yaml
--- a/lm_eval/tasks/blimp_nl/anaphor_agreement__person.yaml
+++ b/lm_eval/tasks/blimp_nl/anaphor_agreement__person.yaml
--- a/lm_eval/tasks/blimp_nl/argument_structure__argument_number_ditransitive.yaml
+++ b/lm_eval/tasks/blimp_nl/argument_structure__argument_number_ditransitive.yaml
--- a/lm_eval/tasks/blimp_nl/argument_structure__argument_number_in_transitive.yaml
+++ b/lm_eval/tasks/blimp_nl/argument_structure__argument_number_in_transitive.yaml
--- a/lm_eval/tasks/blimp_nl/argument_structure__ditransitive_nomdat_1.yaml
+++ b/lm_eval/tasks/blimp_nl/argument_structure__ditransitive_nomdat_1.yaml
--- a/lm_eval/tasks/blimp_nl/argument_structure__ditransitive_nomdat_2.yaml
+++ b/lm_eval/tasks/blimp_nl/argument_structure__ditransitive_nomdat_2.yaml
--- a/lm_eval/tasks/blimp_nl/argument_structure__ditransitive_nomdat_3.yaml
+++ b/lm_eval/tasks/blimp_nl/argument_structure__ditransitive_nomdat_3.yaml
--- a/lm_eval/tasks/blimp_nl/argument_structure__intransitive_unaccusative_1.yaml
+++ b/lm_eval/tasks/blimp_nl/argument_structure__intransitive_unaccusative_1.yaml
--- a/lm_eval/tasks/blimp_nl/argument_structure__intransitive_unaccusative_2.yaml
+++ b/lm_eval/tasks/blimp_nl/argument_structure__intransitive_unaccusative_2.yaml
--- a/lm_eval/tasks/blimp_nl/argument_structure__intransitive_unaccusative_3.yaml
+++ b/lm_eval/tasks/blimp_nl/argument_structure__intransitive_unaccusative_3.yaml
--- a/lm_eval/tasks/blimp_nl/auxiliaries__order_1.yaml
+++ b/lm_eval/tasks/blimp_nl/auxiliaries__order_1.yaml
--- a/lm_eval/tasks/blimp_nl/auxiliaries__order_2.yaml
+++ b/lm_eval/tasks/blimp_nl/auxiliaries__order_2.yaml
--- a/lm_eval/tasks/blimp_nl/auxiliaries__perfect.yaml
+++ b/lm_eval/tasks/blimp_nl/auxiliaries__perfect.yaml
--- a/lm_eval/tasks/blimp_nl/auxiliaries__semi_aspectual_1.yaml
+++ b/lm_eval/tasks/blimp_nl/auxiliaries__semi_aspectual_1.yaml