Merge branch 'main' into longcxt

# Conflicts: # lm_eval/tasks/README.md

Merge branch 'main' into longcxt
# Conflicts: # lm_eval/tasks/README.md
527a4352 · Baber · 6042f622 · 52df63b7 · 527a4352 · 527a4352
Commit 527a4352 authored Feb 20, 2025 by Baber
20 changed files
--- a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_human_aging.yaml
+++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_human_aging.yaml
--- a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_human_sexuality.yaml
+++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_human_sexuality.yaml
--- a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_international_law.yaml
+++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_international_law.yaml
--- a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_jurisprudence.yaml
+++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_jurisprudence.yaml
--- a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_logical_fallacies.yaml
+++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_logical_fallacies.yaml
--- a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_machine_learning.yaml
+++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_machine_learning.yaml
--- a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_management.yaml
+++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_management.yaml
--- a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_marketing.yaml
+++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_marketing.yaml
--- a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_medical_genetics.yaml
+++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_medical_genetics.yaml
--- a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_miscellaneous.yaml
+++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_miscellaneous.yaml
--- a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_moral_disputes.yaml
+++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_moral_disputes.yaml
--- a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_moral_scenarios.yaml
+++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_moral_scenarios.yaml
--- a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_nutrition.yaml
+++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_nutrition.yaml
--- a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_philosophy.yaml
+++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_philosophy.yaml
--- a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_prehistory.yaml
+++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_prehistory.yaml
--- a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_professional_accounting.yaml
+++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_professional_accounting.yaml
--- a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_professional_law.yaml
+++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_professional_law.yaml
--- a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_professional_medicine.yaml
+++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_professional_medicine.yaml
--- a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_professional_psychology.yaml
+++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_professional_psychology.yaml
--- a/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_public_relations.yaml
+++ b/lm_eval/tasks/global_mmlu/full/bn/global_mmlu_full_bn_public_relations.yaml