Add ZhoBLiMP benchmark (#3218)

* add zhoblimp files

* correct group name

* fix group

* add normalized accuracy

lm_eval/tasks/zhoblimp/question_A_not_A_daodi_b.yaml

+dataset_name: question_A_not_A_daodi_b
+include: _template_yaml
+task: zhoblimp_question_A_not_A_daodi_b

lm_eval/tasks/zhoblimp/question_A_not_A_indirect.yaml

+dataset_name: question_A_not_A_indirect
+include: _template_yaml
+task: zhoblimp_question_A_not_A_indirect

lm_eval/tasks/zhoblimp/question_V_not_VP_1.yaml

+dataset_name: question_V_not_VP_1
+include: _template_yaml
+task: zhoblimp_question_V_not_VP_1

lm_eval/tasks/zhoblimp/question_V_not_VP_2.yaml

+dataset_name: question_V_not_VP_2
+include: _template_yaml
+task: zhoblimp_question_V_not_VP_2

lm_eval/tasks/zhoblimp/question_daodi_nandao_1.yaml

+dataset_name: question_daodi_nandao_1
+include: _template_yaml
+task: zhoblimp_question_daodi_nandao_1

lm_eval/tasks/zhoblimp/question_daodi_nandao_2.yaml

+dataset_name: question_daodi_nandao_2
+include: _template_yaml
+task: zhoblimp_question_daodi_nandao_2

lm_eval/tasks/zhoblimp/question_daodi_nandao_A_not_A_intran.yaml

+dataset_name: question_daodi_nandao_A_not_A_intran
+include: _template_yaml
+task: zhoblimp_question_daodi_nandao_A_not_A_intran

lm_eval/tasks/zhoblimp/question_daodi_nandao_A_not_A_tran.yaml

+dataset_name: question_daodi_nandao_A_not_A_tran
+include: _template_yaml
+task: zhoblimp_question_daodi_nandao_A_not_A_tran

lm_eval/tasks/zhoblimp/question_daodi_negation.yaml

+dataset_name: question_daodi_negation
+include: _template_yaml
+task: zhoblimp_question_daodi_negation

lm_eval/tasks/zhoblimp/question_nandao_negation.yaml

+dataset_name: question_nandao_negation
+include: _template_yaml
+task: zhoblimp_question_nandao_negation

lm_eval/tasks/zhoblimp/question_nandao_raising_1_a.yaml

+dataset_name: question_nandao_raising_1_a
+include: _template_yaml
+task: zhoblimp_question_nandao_raising_1_a

lm_eval/tasks/zhoblimp/question_nandao_raising_1_b.yaml

+dataset_name: question_nandao_raising_1_b
+include: _template_yaml
+task: zhoblimp_question_nandao_raising_1_b

lm_eval/tasks/zhoblimp/question_nandao_raising_2.yaml

+dataset_name: question_nandao_raising_2
+include: _template_yaml
+task: zhoblimp_question_nandao_raising_2

lm_eval/tasks/zhoblimp/question_nandao_raising_3.yaml

+dataset_name: question_nandao_raising_3
+include: _template_yaml
+task: zhoblimp_question_nandao_raising_3

lm_eval/tasks/zhoblimp/question_nandao_scope_1.yaml

+dataset_name: question_nandao_scope_1
+include: _template_yaml
+task: zhoblimp_question_nandao_scope_1

lm_eval/tasks/zhoblimp/question_nandao_scope_2.yaml

+dataset_name: question_nandao_scope_2
+include: _template_yaml
+task: zhoblimp_question_nandao_scope_2

lm_eval/tasks/zhoblimp/question_particle_daodi_choice_intran.yaml

+dataset_name: question_particle_daodi_choice_intran
+include: _template_yaml
+task: zhoblimp_question_particle_daodi_choice_intran

lm_eval/tasks/zhoblimp/question_particle_daodi_choice_tran.yaml

+dataset_name: question_particle_daodi_choice_tran
+include: _template_yaml
+task: zhoblimp_question_particle_daodi_choice_tran

lm_eval/tasks/zhoblimp/question_particle_nandao.yaml

+dataset_name: question_particle_nandao
+include: _template_yaml
+task: zhoblimp_question_particle_nandao

lm_eval/tasks/zhoblimp/relative_operator_intepretation.yaml

+dataset_name: relative_operator_intepretation
+include: _template_yaml
+task: zhoblimp_relative_operator_intepretation