MatinaAI/persian_bbh
收藏Hugging Face2024-09-09 更新2025-04-12 收录
下载链接：
https://hf-mirror.com/datasets/MatinaAI/persian_bbh
下载链接
链接失效反馈官方服务：
资源简介：
---
language:
- fa
size_categories:
- 1K<n<10K
task_categories:
- question-answering
pretty_name: PersianBBH
dataset_info:
- config_name: causal_judgement
features:
- name: input
dtype: string
- name: target
sequence: string
splits:
- name: train
num_bytes: 330050
num_examples: 187
download_size: 538099
dataset_size: 661319
- config_name: cot
features:
- name: category
dtype: string
- name: cot
dtype: string
splits:
- name: train
num_bytes: 79940
num_examples: 19
download_size: 23989
dataset_size: 79940
- config_name: date_understanding
features:
- name: input
dtype: string
- name: target
sequence: string
splits:
- name: train
num_bytes: 83260
num_examples: 250
download_size: 57774
dataset_size: 166520
- config_name: disambiguation_qa
features:
- name: input
dtype: string
- name: target
sequence: string
splits:
- name: train
num_bytes: 115334
num_examples: 250
download_size: 120524
dataset_size: 230668
- config_name: dyck_languages
features:
- name: input
dtype: string
- name: target
dtype: string
splits:
- name: train
num_bytes: 52667
num_examples: 250
download_size: 25392
dataset_size: 105334
- config_name: formal_fallacies
features:
- name: input
dtype: string
- name: target
sequence: string
splits:
- name: train
num_bytes: 238028
num_examples: 250
download_size: 145232
dataset_size: 476524
- config_name: logical_deduction_five_objects
features:
- name: input
dtype: string
- name: target
sequence: string
splits:
- name: train
num_bytes: 247766
num_examples: 250
download_size: 120560
dataset_size: 495532
- config_name: logical_deduction_seven_objects
features:
- name: input
dtype: string
- name: target
sequence: string
splits:
- name: train
num_bytes: 314599
num_examples: 250
download_size: 156322
dataset_size: 629198
- config_name: logical_deduction_three_objects
features:
- name: input
dtype: string
- name: target
sequence: string
splits:
- name: train
num_bytes: 178420
num_examples: 250
download_size: 84750
dataset_size: 356840
- config_name: multistep_arithmetic_two
features:
- name: input
dtype: string
- name: target
dtype: int64
splits:
- name: train
num_bytes: 13245
num_examples: 250
download_size: 15164
dataset_size: 26490
- config_name: navigate
features:
- name: input
dtype: string
- name: target
sequence: string
splits:
- name: train
num_bytes: 91645
num_examples: 250
download_size: 31379
dataset_size: 184895
- config_name: object_counting
features:
- name: input
dtype: string
- name: target
dtype: int64
splits:
- name: train
num_bytes: 41989
num_examples: 250
download_size: 39501
dataset_size: 83978
- config_name: penguins_in_a_table
features:
- name: input
dtype: string
- name: target
sequence: string
splits:
- name: train
num_bytes: 107747
num_examples: 146
download_size: 85824
dataset_size: 215494
- config_name: snarks
features:
- name: input
dtype: string
- name: target
sequence: string
splits:
- name: train
num_bytes: 68428
num_examples: 178
download_size: 47418
dataset_size: 136856
- config_name: sports_understanding
features:
- name: input
dtype: string
- name: target
sequence: string
splits:
- name: train
num_bytes: 37523
num_examples: 250
download_size: 25310
dataset_size: 76661
- config_name: temporal_sequences
features:
- name: input
dtype: string
- name: target
sequence: string
splits:
- name: train
num_bytes: 278580
num_examples: 250
download_size: 146798
dataset_size: 557160
- config_name: tracking_shuffled_objects_five_objects
features:
- name: input
dtype: string
- name: target
sequence: string
splits:
- name: train
num_bytes: 289217
num_examples: 250
download_size: 149082
dataset_size: 578434
- config_name: tracking_shuffled_objects_seven_objects
features:
- name: input
dtype: string
- name: target
sequence: string
splits:
- name: train
num_bytes: 369909
num_examples: 250
download_size: 186210
dataset_size: 739818
- config_name: tracking_shuffled_objects_three_objects
features:
- name: input
dtype: string
- name: target
sequence: string
splits:
- name: train
num_bytes: 214888
num_examples: 250
download_size: 219404
dataset_size: 429776
- config_name: web_of_lies
features:
- name: input
dtype: string
- name: target
sequence: string
splits:
- name: train
num_bytes: 101679
num_examples: 250
download_size: 88010
dataset_size: 204980
configs:
- config_name: causal_judgement
data_files:
- split: train
path: causal_judgement/train-*
- config_name: cot
data_files:
- split: train
path: cot/train-*
- config_name: date_understanding
data_files:
- split: train
path: date_understanding/train-*
- config_name: disambiguation_qa
data_files:
- split: train
path: disambiguation_qa/train-*
- config_name: dyck_languages
data_files:
- split: train
path: dyck_languages/train-*
- config_name: formal_fallacies
data_files:
- split: train
path: formal_fallacies/train-*
- config_name: logical_deduction_five_objects
data_files:
- split: train
path: logical_deduction_five_objects/train-*
- config_name: logical_deduction_seven_objects
data_files:
- split: train
path: logical_deduction_seven_objects/train-*
- config_name: logical_deduction_three_objects
data_files:
- split: train
path: logical_deduction_three_objects/train-*
- config_name: multistep_arithmetic_two
data_files:
- split: train
path: multistep_arithmetic_two/train-*
- config_name: navigate
data_files:
- split: train
path: navigate/train-*
- config_name: object_counting
data_files:
- split: train
path: object_counting/train-*
- config_name: penguins_in_a_table
data_files:
- split: train
path: penguins_in_a_table/train-*
- config_name: snarks
data_files:
- split: train
path: snarks/train-*
- config_name: sports_understanding
data_files:
- split: train
path: sports_understanding/train-*
- config_name: temporal_sequences
data_files:
- split: train
path: temporal_sequences/train-*
- config_name: tracking_shuffled_objects_five_objects
data_files:
- split: train
path: tracking_shuffled_objects_five_objects/train-*
- config_name: tracking_shuffled_objects_seven_objects
data_files:
- split: train
path: tracking_shuffled_objects_seven_objects/train-*
- config_name: tracking_shuffled_objects_three_objects
data_files:
- split: train
path: tracking_shuffled_objects_three_objects/train-*
- config_name: web_of_lies
data_files:
- split: train
path: web_of_lies/train-*
---
# Persian BBH
This is [BIG-bench Hard](https://github.com/suzgunmirac/BIG-Bench-Hard) dataset translated to Persian using GPT-4o-mini.
We use 19 out of 23 original tasks in BIG-bench Hard.
提供机构：
MatinaAI
