YYYYYYibo/eval-dataset-with-score-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
- name: gpt_score
dtype: int64
splits:
- name: train_prefs
num_bytes: 1980786
num_examples: 200
download_size: 1143455
dataset_size: 1980786
configs:
- config_name: default
data_files:
- split: train_prefs
path: data/train_prefs-*
---
# Dataset Card for "eval-dataset-with-score-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

"eval-dataset-with-score-nash"

数据集特征

• prompt: 数据类型 - string
• prompt_id: 数据类型 - string
• chosen:
  • content: 数据类型 - string
  • role: 数据类型 - string
• rejected:
  • content: 数据类型 - string
  • role: 数据类型 - string
• messages:
  • content: 数据类型 - string
  • role: 数据类型 - string
• score_chosen: 数据类型 - float64
• score_rejected: 数据类型 - float64
• reference_response: 数据类型 - string
• original: 数据类型 - string
• nash: 数据类型 - string
• gpt_score: 数据类型 - int64

数据集分割

• train_prefs:
  • 字节数: 1980786
  • 示例数: 200

数据集大小

• 下载大小: 1143455
• 数据集大小: 1980786

配置

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