supergoose/sentence_transformer_kmeans100_viewer

---
dataset_info:
features:
- name: dataset
dtype: string
- name: id
dtype: string
- name: messages
list:
- name: role
dtype: string
- name: content
dtype: string
configs:
- config_name: '0'
data_files:
- split: "train"
path: data/0-*
- config_name: '1'
data_files:
- split: "train"
path: data/1-*
- config_name: '2'
data_files:
- split: "train"
path: data/2-*
- config_name: '3'
data_files:
- split: "train"
path: data/3-*
- config_name: '4'
data_files:
- split: "train"
path: data/4-*
- config_name: '5'
data_files:
- split: "train"
path: data/5-*
- config_name: '6'
data_files:
- split: "train"
path: data/6-*
- config_name: '7'
data_files:
- split: "train"
path: data/7-*
- config_name: '8'
data_files:
- split: "train"
path: data/8-*
- config_name: '9'
data_files:
- split: "train"
path: data/9-*
- config_name: '10'
data_files:
- split: "train"
path: data/10-*
- config_name: '11'
data_files:
- split: "train"
path: data/11-*
- config_name: '12'
data_files:
- split: "train"
path: data/12-*
- config_name: '13'
data_files:
- split: "train"
path: data/13-*
- config_name: '14'
data_files:
- split: "train"
path: data/14-*
- config_name: '15'
data_files:
- split: "train"
path: data/15-*
- config_name: '16'
data_files:
- split: "train"
path: data/16-*
- config_name: '17'
data_files:
- split: "train"
path: data/17-*
- config_name: '18'
data_files:
- split: "train"
path: data/18-*
- config_name: '19'
data_files:
- split: "train"
path: data/19-*
- config_name: '20'
data_files:
- split: "train"
path: data/20-*
- config_name: '21'
data_files:
- split: "train"
path: data/21-*
- config_name: '22'
data_files:
- split: "train"
path: data/22-*
- config_name: '23'
data_files:
- split: "train"
path: data/23-*
- config_name: '24'
data_files:
- split: "train"
path: data/24-*
- config_name: '25'
data_files:
- split: "train"
path: data/25-*
- config_name: '26'
data_files:
- split: "train"
path: data/26-*
- config_name: '27'
data_files:
- split: "train"
path: data/27-*
- config_name: '28'
data_files:
- split: "train"
path: data/28-*
- config_name: '29'
data_files:
- split: "train"
path: data/29-*
- config_name: '30'
data_files:
- split: "train"
path: data/30-*
- config_name: '31'
data_files:
- split: "train"
path: data/31-*
- config_name: '32'
data_files:
- split: "train"
path: data/32-*
- config_name: '33'
data_files:
- split: "train"
path: data/33-*
- config_name: '34'
data_files:
- split: "train"
path: data/34-*
- config_name: '35'
data_files:
- split: "train"
path: data/35-*
- config_name: '36'
data_files:
- split: "train"
path: data/36-*
- config_name: '37'
data_files:
- split: "train"
path: data/37-*
- config_name: '38'
data_files:
- split: "train"
path: data/38-*
- config_name: '39'
data_files:
- split: "train"
path: data/39-*
- config_name: '40'
data_files:
- split: "train"
path: data/40-*
- config_name: '41'
data_files:
- split: "train"
path: data/41-*
- config_name: '42'
data_files:
- split: "train"
path: data/42-*
- config_name: '43'
data_files:
- split: "train"
path: data/43-*
- config_name: '44'
data_files:
- split: "train"
path: data/44-*
- config_name: '45'
data_files:
- split: "train"
path: data/45-*
- config_name: '46'
data_files:
- split: "train"
path: data/46-*
- config_name: '47'
data_files:
- split: "train"
path: data/47-*
- config_name: '48'
data_files:
- split: "train"
path: data/48-*
- config_name: '49'
data_files:
- split: "train"
path: data/49-*
- config_name: '50'
data_files:
- split: "train"
path: data/50-*
- config_name: '51'
data_files:
- split: "train"
path: data/51-*
- config_name: '52'
data_files:
- split: "train"
path: data/52-*
- config_name: '53'
data_files:
- split: "train"
path: data/53-*
- config_name: '54'
data_files:
- split: "train"
path: data/54-*
- config_name: '55'
data_files:
- split: "train"
path: data/55-*
- config_name: '56'
data_files:
- split: "train"
path: data/56-*
- config_name: '57'
data_files:
- split: "train"
path: data/57-*
- config_name: '58'
data_files:
- split: "train"
path: data/58-*
- config_name: '59'
data_files:
- split: "train"
path: data/59-*
- config_name: '60'
data_files:
- split: "train"
path: data/60-*
- config_name: '61'
data_files:
- split: "train"
path: data/61-*
- config_name: '62'
data_files:
- split: "train"
path: data/62-*
- config_name: '63'
data_files:
- split: "train"
path: data/63-*
- config_name: '64'
data_files:
- split: "train"
path: data/64-*
- config_name: '65'
data_files:
- split: "train"
path: data/65-*
- config_name: '66'
data_files:
- split: "train"
path: data/66-*
- config_name: '67'
data_files:
- split: "train"
path: data/67-*
- config_name: '68'
data_files:
- split: "train"
path: data/68-*
- config_name: '69'
data_files:
- split: "train"
path: data/69-*
- config_name: '70'
data_files:
- split: "train"
path: data/70-*
- config_name: '71'
data_files:
- split: "train"
path: data/71-*
- config_name: '72'
data_files:
- split: "train"
path: data/72-*
- config_name: '73'
data_files:
- split: "train"
path: data/73-*
- config_name: '74'
data_files:
- split: "train"
path: data/74-*
- config_name: '75'
data_files:
- split: "train"
path: data/75-*
- config_name: '76'
data_files:
- split: "train"
path: data/76-*
- config_name: '77'
data_files:
- split: "train"
path: data/77-*
- config_name: '78'
data_files:
- split: "train"
path: data/78-*
- config_name: '79'
data_files:
- split: "train"
path: data/79-*
- config_name: '80'
data_files:
- split: "train"
path: data/80-*
- config_name: '81'
data_files:
- split: "train"
path: data/81-*
- config_name: '82'
data_files:
- split: "train"
path: data/82-*
- config_name: '83'
data_files:
- split: "train"
path: data/83-*
- config_name: '84'
data_files:
- split: "train"
path: data/84-*
- config_name: '85'
data_files:
- split: "train"
path: data/85-*
- config_name: '86'
data_files:
- split: "train"
path: data/86-*
- config_name: '87'
data_files:
- split: "train"
path: data/87-*
- config_name: '88'
data_files:
- split: "train"
path: data/88-*
- config_name: '89'
data_files:
- split: "train"
path: data/89-*
- config_name: '90'
data_files:
- split: "train"
path: data/90-*
- config_name: '91'
data_files:
- split: "train"
path: data/91-*
- config_name: '92'
data_files:
- split: "train"
path: data/92-*
- config_name: '93'
data_files:
- split: "train"
path: data/93-*
- config_name: '94'
data_files:
- split: "train"
path: data/94-*
- config_name: '95'
data_files:
- split: "train"
path: data/95-*
- config_name: '96'
data_files:
- split: "train"
path: data/96-*
- config_name: '97'
data_files:
- split: "train"
path: data/97-*
- config_name: '98'
data_files:
- split: "train"
path: data/98-*
- config_name: '99'
data_files:
- split: "train"
path: data/99-*
---

The dataset includes features such as dataset, id, and messages, where messages is a list containing role and content. The dataset is divided into multiple configurations, each identified by a number (from 0 to 99) and each configuration has a train split with corresponding data files located in the data/ directory, named with the configuration number followed by an asterisk (*).

原始信息汇总

数据集概述

数据集特征

• dataset: 数据类型为字符串（string）。
• id: 数据类型为字符串（string）。
• messages: 包含以下子特征：
  • role: 数据类型为字符串（string）。
  • content: 数据类型为字符串（string）。

数据集配置

• 数据集包含多个配置，每个配置对应一个唯一的config_name，范围从0到99。
• 每个配置包含一个数据文件，其split属性为"train"，path属性遵循模式data/[config_name]-*。