gimmaru/super_glue-copa
收藏Hugging Face2023-12-24 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/gimmaru/super_glue-copa
下载链接
链接失效反馈官方服务:
资源简介:
---
dataset_info:
features:
- name: premise
dtype: string
- name: choice1
dtype: string
- name: choice2
dtype: string
- name: question
dtype: string
- name: idx
dtype: int32
- name: label
dtype:
class_label:
names:
'0': choice1
'1': choice2
splits:
- name: validation
num_bytes: 12479
num_examples: 100
download_size: 0
dataset_size: 12479
---
# Dataset Card for "super_glue-copa"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
Note: This dataset was utilized for the evaluation of probability-based prompt selection techniques in the paper '[Improving Probability-based Prompt Selection Through Unified Evaluation and Analysis](https://arxiv.org/abs/2305.14877)'. It differs from the actual benchmark dataset.
提供机构:
gimmaru
原始信息汇总
数据集概述
数据集名称
super_glue-copa
数据集特征
- premise:字符串类型
- choice1:字符串类型
- choice2:字符串类型
- question:字符串类型
- idx:整数类型(int32)
- label:分类标签,其中:
- 0 对应 choice1
- 1 对应 choice2
数据集分割
- validation:
- 示例数量:100
- 数据大小:12479字节
数据集大小
- 下载大小:0字节
- 数据集总大小:12479字节



