explodinggradients/wiki-eval

---
dataset_info:
features:
- name: answer
dtype: string
- name: source
dtype: string
- name: context_retrieved
sequence: string
- name: grounded_answer
dtype: string
- name: question
dtype: string
- name: answer_v2
dtype: string
- name: answer_v1
dtype: string
- name: answer_vinuca_grounded
dtype: string
- name: partial_answer
dtype: string
- name: answer_relevancy_v1
dtype: string
- name: answer_relevancy_v1_relscore
dtype: float64
- name: answer_relscore
dtype: float64
- name: answer_v1_relscore
dtype: float64
- name: context_v2
sequence: string
- name: context_v1
sequence: string
- name: context_v1_score
dtype: float64
- name: context_v2_score
dtype: float64
splits:
- name: train
num_bytes: 999168
num_examples: 50
download_size: 649442
dataset_size: 999168
---
# Dataset Card for "wiki-eval"

[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

原始信息汇总

数据集概述

数据集特征

• answer: 字符串类型
• source: 字符串类型
• context_retrieved: 字符串序列
• grounded_answer: 字符串类型
• question: 字符串类型
• answer_v2: 字符串类型
• answer_v1: 字符串类型
• answer_vinuca_grounded: 字符串类型
• partial_answer: 字符串类型
• answer_relevancy_v1: 字符串类型
• answer_relevancy_v1_relscore: 浮点数类型（float64）
• answer_relscore: 浮点数类型（float64）
• answer_v1_relscore: 浮点数类型（float64）
• context_v2: 字符串序列
• context_v1: 字符串序列
• context_v1_score: 浮点数类型（float64）
• context_v2_score: 浮点数类型（float64）

数据集分割

• train:
  • 数据量: 999168字节
  • 示例数量: 50

数据集大小

• 下载大小: 649442字节
• 数据集大小: 999168字节