metadata

license: apache-2.0
task_categories:
  - text-generation
  - summarization
  - question-answering
language:
  - en
tags:
  - Empathetic
  - Context
  - biology
  - medical
  - climate
size_categories:
  - 100K<n<1M

Synthetic-Context-Conversations

Overview

The Synthetic-Context-Conversations dataset is a collection of synthetic conversations designed to simulate empathetic and context-rich dialogues. It is particularly useful for tasks such as text generation, summarization, and question answering. The dataset is available in English and contains between 10,000 to 100,000 entries.

Dataset Details

Modalities: Text
Languages: English
Size: 10K-100K
Formats: Parquet
License: Apache-2.0

Dataset Structure

The dataset is split into a single training set with 99,086 rows. Each row contains a conversation between a human and an AI, focusing on various emotional and contextual topics.

Example Conversations

[
  {"from": "human", "value": "I've been feeling so sad and overwhelmed lately, work has become such a massive source of stress for me."},
  {"from": "get", "value": "Hey there, I'm here to listen and support you. It sounds like work has been really challenging lately, can..."}
]

Usage

Console

Size of downloaded dataset files: 448 MB
Size of the adis-connected Parquet files: 210 MB
Number of rows: 99,086