Merge branch 'main' into multimodal-prototyping

e4db76cb · haileyschoelkopf · 6cc6e9cd · ad80f555 · e4db76cb · e4db76cb
Commit e4db76cb authored Jul 09, 2024 by haileyschoelkopf
20 changed files
--- a/lm_eval/tasks/mmlu/generative/mmlu_miscellaneous.yaml
+++ b/lm_eval/tasks/mmlu/generative/mmlu_miscellaneous.yaml
--- a/lm_eval/tasks/mmlu/generative/mmlu_moral_disputes.yaml
+++ b/lm_eval/tasks/mmlu/generative/mmlu_moral_disputes.yaml
--- a/lm_eval/tasks/mmlu/generative/mmlu_moral_scenarios.yaml
+++ b/lm_eval/tasks/mmlu/generative/mmlu_moral_scenarios.yaml
--- a/lm_eval/tasks/mmlu/generative/mmlu_nutrition.yaml
+++ b/lm_eval/tasks/mmlu/generative/mmlu_nutrition.yaml
--- a/lm_eval/tasks/mmlu/generative/mmlu_philosophy.yaml
+++ b/lm_eval/tasks/mmlu/generative/mmlu_philosophy.yaml
--- a/lm_eval/tasks/mmlu/generative/mmlu_prehistory.yaml
+++ b/lm_eval/tasks/mmlu/generative/mmlu_prehistory.yaml
--- a/lm_eval/tasks/mmlu/generative/mmlu_professional_accounting.yaml
+++ b/lm_eval/tasks/mmlu/generative/mmlu_professional_accounting.yaml
--- a/lm_eval/tasks/mmlu/generative/mmlu_professional_law.yaml
+++ b/lm_eval/tasks/mmlu/generative/mmlu_professional_law.yaml
--- a/lm_eval/tasks/mmlu/generative/mmlu_professional_medicine.yaml
+++ b/lm_eval/tasks/mmlu/generative/mmlu_professional_medicine.yaml
--- a/lm_eval/tasks/mmlu/generative/mmlu_professional_psychology.yaml
+++ b/lm_eval/tasks/mmlu/generative/mmlu_professional_psychology.yaml
--- a/lm_eval/tasks/mmlu/generative/mmlu_public_relations.yaml
+++ b/lm_eval/tasks/mmlu/generative/mmlu_public_relations.yaml
--- a/lm_eval/tasks/mmlu/generative/mmlu_security_studies.yaml
+++ b/lm_eval/tasks/mmlu/generative/mmlu_security_studies.yaml
--- a/lm_eval/tasks/mmlu/generative/mmlu_sociology.yaml
+++ b/lm_eval/tasks/mmlu/generative/mmlu_sociology.yaml
--- a/lm_eval/tasks/mmlu/generative/mmlu_us_foreign_policy.yaml
+++ b/lm_eval/tasks/mmlu/generative/mmlu_us_foreign_policy.yaml
--- a/lm_eval/tasks/mmlu/generative/mmlu_virology.yaml
+++ b/lm_eval/tasks/mmlu/generative/mmlu_virology.yaml
--- a/lm_eval/tasks/mmlu/generative/mmlu_world_religions.yaml
+++ b/lm_eval/tasks/mmlu/generative/mmlu_world_religions.yaml
--- a/lm_eval/tasks/model_written_evals/advanced_ai_risk/_template_yaml
+++ b/lm_eval/tasks/model_written_evals/advanced_ai_risk/_template_yaml
--- a/lm_eval/tasks/model_written_evals/persona/_template_yaml
+++ b/lm_eval/tasks/model_written_evals/persona/_template_yaml
--- a/lm_eval/tasks/model_written_evals/sycophancy/sycophancy_on_nlp_survey.yaml
+++ b/lm_eval/tasks/model_written_evals/sycophancy/sycophancy_on_nlp_survey.yaml
--- a/lm_eval/tasks/model_written_evals/sycophancy/sycophancy_on_philpapers2020.yaml
+++ b/lm_eval/tasks/model_written_evals/sycophancy/sycophancy_on_philpapers2020.yaml