init

3041681f · silencealiang · 291fc518 · 3041681f · 3041681f · 3041681f
Commit 3041681f authored Mar 19, 2025 by silencealiang
20 changed files
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/regular_plural_subject_verb_agreement_1.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/regular_plural_subject_verb_agreement_1.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/regular_plural_subject_verb_agreement_2.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/regular_plural_subject_verb_agreement_2.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/sentential_negation_npi_licensor_present.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/sentential_negation_npi_licensor_present.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/sentential_negation_npi_scope.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/sentential_negation_npi_scope.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/sentential_subject_island.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/sentential_subject_island.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/superlative_quantifiers_1.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/superlative_quantifiers_1.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/superlative_quantifiers_2.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/superlative_quantifiers_2.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/tough_vs_raising_1.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/tough_vs_raising_1.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/tough_vs_raising_2.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/tough_vs_raising_2.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/transitive.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/transitive.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/wh_island.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/wh_island.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/wh_questions_object_gap.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/wh_questions_object_gap.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/wh_questions_subject_gap.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/wh_questions_subject_gap.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/wh_questions_subject_gap_long_distance.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/wh_questions_subject_gap_long_distance.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/wh_vs_that_no_gap.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/wh_vs_that_no_gap.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/wh_vs_that_no_gap_long_distance.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/wh_vs_that_no_gap_long_distance.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/wh_vs_that_with_gap.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/wh_vs_that_with_gap.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/wh_vs_that_with_gap_long_distance.yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/blimp/wh_vs_that_with_gap_long_distance.yaml
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/ceval/README.md
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/ceval/README.md
--- a/LM-Evaluation-Harness-240310/lm_eval/tasks/ceval/_default_ceval_yaml
+++ b/LM-Evaluation-Harness-240310/lm_eval/tasks/ceval/_default_ceval_yaml