mradermacher/Mochi-2B-GGUF
2B β’ Updated β’ 199
Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.
This dataset contains 500,000 high-quality conversational entries focused on emotional support and empathy. It is formatted in the OpenAI Chat format, making it compatible with most modern fine-tuning pipelines.
{
"messages": [
{
"role": "system",
"content": "You are an empathetic emotional support assistant."
},
{
"role": "user",
"content": "I feel like I'm a failure. What can I do?"
},
{
"role": "assistant",
"content": "Let's challenge that thought together. Can you think of a recent success, no matter how small? Hold on to that spark. Small steps today can lead to real change."
}
]
}
This dataset is designed for:
You can load this dataset using the Hugging Face datasets library:
from datasets import load_dataset
dataset = load_dataset("your-username/emotional_support_500k")
Licensed under the Apache License 2.0. You are free to use, modify, and distribute this dataset.
Dream it, Pixel it β¨