Merge branch 'main' into metrics

# Conflicts: # .pre-commit-config.yaml # lm_eval/api/task.py # lm_eval/models/huggingface.py # lm_eval/models/vllm_causallms.py # pyproject.toml

Merge branch 'main' into metrics
# Conflicts: # .pre-commit-config.yaml # lm_eval/api/task.py # lm_eval/models/huggingface.py # lm_eval/models/vllm_causallms.py # pyproject.toml
e6b798f9 · Baber · 14a29ade · 4f8195f1 · e6b798f9 · e6b798f9
Commit e6b798f9 authored Jul 25, 2025 by Baber
20 changed files
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/_mmlu_flan_cot_zeroshot_template_yaml
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/_mmlu_flan_cot_zeroshot_template_yaml
--- a/lm_eval/tasks/mmlu/flan_cot_zeroshot/utils.py
+++ b/lm_eval/tasks/mmlu/flan_cot_zeroshot/utils.py
--- a/lm_eval/tasks/mmlu/flan_n_shot/generative/_mmlu_flan_generative_template_yaml
+++ b/lm_eval/tasks/mmlu/flan_n_shot/generative/_mmlu_flan_generative_template_yaml
--- a/lm_eval/tasks/mmlu/flan_n_shot/generative/utils.py
+++ b/lm_eval/tasks/mmlu/flan_n_shot/generative/utils.py
--- a/lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/_mmlu_flan_loglikelihood_template_yaml
+++ b/lm_eval/tasks/mmlu/flan_n_shot/loglikelihood/_mmlu_flan_loglikelihood_template_yaml
--- a/lm_eval/tasks/mmlu/generative/_default_template_yaml
+++ b/lm_eval/tasks/mmlu/generative/_default_template_yaml
--- a/lm_eval/tasks/mmlu_prox/mmlu_prox_config_generator.py
+++ b/lm_eval/tasks/mmlu_prox/mmlu_prox_config_generator.py
--- 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
--- a/lm_eval/tasks/model_written_evals/sycophancy/sycophancy_on_political_typology_quiz.yaml
+++ b/lm_eval/tasks/model_written_evals/sycophancy/sycophancy_on_political_typology_quiz.yaml
--- a/lm_eval/tasks/mutual/mutual.yaml
+++ b/lm_eval/tasks/mutual/mutual.yaml
--- a/lm_eval/tasks/noreval/tatoeba/_tatoeba_yaml
+++ b/lm_eval/tasks/noreval/tatoeba/_tatoeba_yaml
--- a/lm_eval/tasks/piqa/piqa.yaml
+++ b/lm_eval/tasks/piqa/piqa.yaml
--- a/lm_eval/tasks/portuguese_bench/flores_pt/_flores_common_yaml
+++ b/lm_eval/tasks/portuguese_bench/flores_pt/_flores_common_yaml
--- a/lm_eval/tasks/race/race.yaml
+++ b/lm_eval/tasks/race/race.yaml
--- a/lm_eval/tasks/score/agi_eval/non_greedy_robustness_agieval_aqua_rat.yaml
+++ b/lm_eval/tasks/score/agi_eval/non_greedy_robustness_agieval_aqua_rat.yaml
--- a/lm_eval/tasks/score/agi_eval/option_order_robustness_agieval_aqua_rat.yaml
+++ b/lm_eval/tasks/score/agi_eval/option_order_robustness_agieval_aqua_rat.yaml
--- a/lm_eval/tasks/score/agi_eval/prompt_robustness_agieval_aqua_rat.yaml
+++ b/lm_eval/tasks/score/agi_eval/prompt_robustness_agieval_aqua_rat.yaml
--- a/lm_eval/tasks/score/math/math_grader.py
+++ b/lm_eval/tasks/score/math/math_grader.py
--- a/lm_eval/tasks/score/math/non_greedy_robustness_math_algebra.yaml
+++ b/lm_eval/tasks/score/math/non_greedy_robustness_math_algebra.yaml