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/paws-x/paws_ja.yaml
+++ b/lm_eval/tasks/paws-x/paws_ja.yaml
--- a/lm_eval/tasks/paws-x/paws_ko.yaml
+++ b/lm_eval/tasks/paws-x/paws_ko.yaml
--- a/lm_eval/tasks/paws-x/paws_zh.yaml
+++ b/lm_eval/tasks/paws-x/paws_zh.yaml
--- a/lm_eval/tasks/paws-x/pawsx_template_yaml
+++ b/lm_eval/tasks/paws-x/pawsx_template_yaml
--- a/lm_eval/tasks/score/NON_GREEDY.md
+++ b/lm_eval/tasks/score/NON_GREEDY.md
--- a/lm_eval/tasks/score/README.md
+++ b/lm_eval/tasks/score/README.md
--- 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/non_greedy_robustness_agieval_logiqa_en.yaml
+++ b/lm_eval/tasks/score/agi_eval/non_greedy_robustness_agieval_logiqa_en.yaml
--- a/lm_eval/tasks/score/agi_eval/non_greedy_robustness_agieval_lsat_rc.yaml
+++ b/lm_eval/tasks/score/agi_eval/non_greedy_robustness_agieval_lsat_rc.yaml
--- a/lm_eval/tasks/score/agi_eval/non_greedy_robustness_agieval_lstat_ar.yaml
+++ b/lm_eval/tasks/score/agi_eval/non_greedy_robustness_agieval_lstat_ar.yaml
--- a/lm_eval/tasks/score/agi_eval/non_greedy_robustness_agieval_lstat_lr.yaml
+++ b/lm_eval/tasks/score/agi_eval/non_greedy_robustness_agieval_lstat_lr.yaml
--- a/lm_eval/tasks/score/agi_eval/non_greedy_robustness_agieval_sat_en.yaml
+++ b/lm_eval/tasks/score/agi_eval/non_greedy_robustness_agieval_sat_en.yaml
--- a/lm_eval/tasks/score/agi_eval/non_greedy_robustness_agieval_sat_math.yaml
+++ b/lm_eval/tasks/score/agi_eval/non_greedy_robustness_agieval_sat_math.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/option_order_robustness_agieval_logiqa_en.yaml
+++ b/lm_eval/tasks/score/agi_eval/option_order_robustness_agieval_logiqa_en.yaml
--- a/lm_eval/tasks/score/agi_eval/option_order_robustness_agieval_lsat_ar.yaml
+++ b/lm_eval/tasks/score/agi_eval/option_order_robustness_agieval_lsat_ar.yaml
--- a/lm_eval/tasks/score/agi_eval/option_order_robustness_agieval_lsat_lr.yaml
+++ b/lm_eval/tasks/score/agi_eval/option_order_robustness_agieval_lsat_lr.yaml
--- a/lm_eval/tasks/score/agi_eval/option_order_robustness_agieval_lsat_rc.yaml
+++ b/lm_eval/tasks/score/agi_eval/option_order_robustness_agieval_lsat_rc.yaml
--- a/lm_eval/tasks/score/agi_eval/option_order_robustness_agieval_sat_en.yaml
+++ b/lm_eval/tasks/score/agi_eval/option_order_robustness_agieval_sat_en.yaml
--- a/lm_eval/tasks/score/agi_eval/option_order_robustness_agieval_sat_math.yaml
+++ b/lm_eval/tasks/score/agi_eval/option_order_robustness_agieval_sat_math.yaml