YYYYYYibo/eval-dataset-nash

---
dataset_info:
features:
- name: prompt
dtype: string
- name: prompt_id
dtype: string
- name: chosen
list:
- name: content
dtype: string
- name: role
dtype: string
- name: rejected
list:
- name: content
dtype: string
- name: role
dtype: string
- name: messages
list:
- name: content
dtype: string
- name: role
dtype: string
- name: score_chosen
dtype: float64
- name: score_rejected
dtype: float64
- name: reference_response
dtype: string
- name: original
dtype: string
- name: nash
dtype: string
splits:
- name: train_prefs
num_bytes: 10443725
num_examples: 1000
download_size: 5632756
dataset_size: 10443725
configs:
- config_name: default
data_files:
- split: train_prefs
path: data/train_prefs-*
---
# Dataset Card for "eval-dataset-nash"

[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

数据集名称

• 名称: eval-dataset-nash

数据集特征

• prompt: 字符串类型
• prompt_id: 字符串类型
• chosen: 列表类型，包含
  • content: 字符串类型
  • role: 字符串类型
• rejected: 列表类型，包含
  • content: 字符串类型
  • role: 字符串类型
• messages: 列表类型，包含
  • content: 字符串类型
  • role: 字符串类型
• score_chosen: 浮点数类型
• score_rejected: 浮点数类型
• reference_response: 字符串类型
• original: 字符串类型
• nash: 字符串类型

数据集分割

• train_prefs:
  • num_bytes: 10443725
  • num_examples: 1000

数据集大小

• download_size: 5632756
• dataset_size: 10443725

配置

• config_name: default
• data_files:
  • split: train_prefs
  • path: data/train_prefs-*