Merge branch 'main' into mathvista

# Conflicts: # lm_eval/models/openai_completions.py

Merge branch 'main' into mathvista
# Conflicts: # lm_eval/models/openai_completions.py
2106fbeb · Baber · 4354fe46 · 703fbffd · 2106fbeb · 2106fbeb
Commit 2106fbeb authored Jan 15, 2025 by Baber
20 changed files
--- a/lm_eval/tasks/kbl/bar_exam/public/kbl_bar_exam_em_public_2020.yaml
+++ b/lm_eval/tasks/kbl/bar_exam/public/kbl_bar_exam_em_public_2020.yaml
--- a/lm_eval/tasks/kbl/bar_exam/public/kbl_bar_exam_em_public_2021.yaml
+++ b/lm_eval/tasks/kbl/bar_exam/public/kbl_bar_exam_em_public_2021.yaml
--- a/lm_eval/tasks/kbl/bar_exam/public/kbl_bar_exam_em_public_2022.yaml
+++ b/lm_eval/tasks/kbl/bar_exam/public/kbl_bar_exam_em_public_2022.yaml
--- a/lm_eval/tasks/kbl/bar_exam/public/kbl_bar_exam_em_public_2023.yaml
+++ b/lm_eval/tasks/kbl/bar_exam/public/kbl_bar_exam_em_public_2023.yaml
--- a/lm_eval/tasks/kbl/bar_exam/public/kbl_bar_exam_em_public_2024.yaml
+++ b/lm_eval/tasks/kbl/bar_exam/public/kbl_bar_exam_em_public_2024.yaml
--- a/lm_eval/tasks/kbl/bar_exam/responsibility/_base_em_yaml
+++ b/lm_eval/tasks/kbl/bar_exam/responsibility/_base_em_yaml
--- a/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2010.yaml
+++ b/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2010.yaml
--- a/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2011.yaml
+++ b/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2011.yaml
--- a/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2012.yaml
+++ b/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2012.yaml
--- a/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2013.yaml
+++ b/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2013.yaml
--- a/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2014.yaml
+++ b/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2014.yaml
--- a/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2015.yaml
+++ b/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2015.yaml
--- a/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2016.yaml
+++ b/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2016.yaml
--- a/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2017.yaml
+++ b/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2017.yaml
--- a/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2018.yaml
+++ b/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2018.yaml
--- a/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2019.yaml
+++ b/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2019.yaml
--- a/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2020.yaml
+++ b/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2020.yaml
--- a/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2021.yaml
+++ b/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2021.yaml
--- a/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2022.yaml
+++ b/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2022.yaml
--- a/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2023.yaml
+++ b/lm_eval/tasks/kbl/bar_exam/responsibility/kbl_bar_exam_em_responsibility_2023.yaml