Add ZhoBLiMP benchmark (#3218)

* add zhoblimp files

* correct group name

* fix group

* add normalized accuracy

lm_eval/tasks/zhoblimp/_template_yaml

+dataset_path: Junrui1202/zhoblimp
+output_type: multiple_choice
+test_split: train
+doc_to_text: ""
+target_delimiter: ""
+doc_to_target: 0
+doc_to_choice: "{{[sentence_good, sentence_bad]}}"
+num_fewshot: 0
+metric_list:
+  - metric: acc
+    aggregation: mean
+    higher_is_better: true
+metadata:
+  version: 0

lm_eval/tasks/zhoblimp/adjective_transitive_dui.yaml

+dataset_name: adjective_transitive_dui
+include: _template_yaml
+task: zhoblimp_adjective_transitive_dui

lm_eval/tasks/zhoblimp/agent_animacy_adv.yaml

+dataset_name: agent_animacy_adv
+include: _template_yaml
+task: zhoblimp_agent_animacy_adv

lm_eval/tasks/zhoblimp/agent_animacy_passive.yaml

+dataset_name: agent_animacy_passive
+include: _template_yaml
+task: zhoblimp_agent_animacy_passive

lm_eval/tasks/zhoblimp/agent_animacy_subj.yaml

+dataset_name: agent_animacy_subj
+include: _template_yaml
+task: zhoblimp_agent_animacy_subj

lm_eval/tasks/zhoblimp/agent_causative.yaml

+dataset_name: agent_causative
+include: _template_yaml
+task: zhoblimp_agent_causative

lm_eval/tasks/zhoblimp/agent_deletion.yaml

+dataset_name: agent_deletion
+include: _template_yaml
+task: zhoblimp_agent_deletion

lm_eval/tasks/zhoblimp/anaphor_gender_agreement.yaml

+dataset_name: anaphor_gender_agreement
+include: _template_yaml
+task: zhoblimp_anaphor_gender_agreement

lm_eval/tasks/zhoblimp/anaphor_number_agreement.yaml

+dataset_name: anaphor_number_agreement
+include: _template_yaml
+task: zhoblimp_anaphor_number_agreement

lm_eval/tasks/zhoblimp/causative_shi_ba.yaml

+dataset_name: causative_shi_ba
+include: _template_yaml
+task: zhoblimp_causative_shi_ba

lm_eval/tasks/zhoblimp/classifier_noun_agreement.yaml

+dataset_name: classifier_noun_agreement
+include: _template_yaml
+task: zhoblimp_classifier_noun_agreement

lm_eval/tasks/zhoblimp/classifier_noun_agreement_no_gap.yaml

+dataset_name: classifier_noun_agreement_no_gap
+include: _template_yaml
+task: zhoblimp_classifier_noun_agreement_no_gap

lm_eval/tasks/zhoblimp/classifier_noun_subj.yaml

+dataset_name: classifier_noun_subj
+include: _template_yaml
+task: zhoblimp_classifier_noun_subj

lm_eval/tasks/zhoblimp/control_modal_vs_raising_modal.yaml

+dataset_name: control_modal_vs_raising_modal
+include: _template_yaml
+task: zhoblimp_control_modal_vs_raising_modal

lm_eval/tasks/zhoblimp/ellipsis_adj.yaml

+dataset_name: ellipsis_adj
+include: _template_yaml
+task: zhoblimp_ellipsis_adj

lm_eval/tasks/zhoblimp/ellipsis_double_object.yaml

+dataset_name: ellipsis_double_object
+include: _template_yaml
+task: zhoblimp_ellipsis_double_object

lm_eval/tasks/zhoblimp/ellipsis_n_bar_class.yaml

+dataset_name: ellipsis_n_bar_class
+include: _template_yaml
+task: zhoblimp_ellipsis_n_bar_class

lm_eval/tasks/zhoblimp/existential_there_subject_raising.yaml

+dataset_name: existential_there_subject_raising
+include: _template_yaml
+task: zhoblimp_existential_there_subject_raising

lm_eval/tasks/zhoblimp/fci_renhe_dou.yaml

+dataset_name: fci_renhe_dou
+include: _template_yaml
+task: zhoblimp_fci_renhe_dou

lm_eval/tasks/zhoblimp/fci_renhe_prepP.yaml

+dataset_name: fci_renhe_prepP
+include: _template_yaml
+task: zhoblimp_fci_renhe_prepP