DIBT/aya_english_dpo_raw

---
size_categories: n<1K
dataset_info:
features:
- name: instruction
dtype: string
- name: targets
dtype: string
- name: language
dtype: string
- name: language_code
dtype: string
- name: annotation_type
dtype: string
- name: user_id
dtype: string
- name: generation_model
dtype: string
- name: generation
dtype: string
- name: predicted_generation_language
dtype: string
- name: predicted_generation_language_score
dtype: float64
- name: generations
sequence: string
- name: generation_models
sequence: string
- name: model_name
dtype: string
- name: ratings
sequence: int64
- name: rationales
sequence: string
splits:
- name: train
num_bytes: 567777
num_examples: 100
download_size: 320089
dataset_size: 567777
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
tags:
- synthetic
- distilabel
- rlaif
---

<p align="left">
<a href="https://github.com/argilla-io/distilabel">
<img src="https://raw.githubusercontent.com/argilla-io/distilabel/main/docs/assets/distilabel-badge-light.png" alt="Built with Distilabel" width="200" height="32"/>
</a>
</p>

# Dataset Card for aya_english_dpo_raw

This dataset has been created with [distilabel](https://distilabel.argilla.io/).

## Dataset Summary

This dataset contains a `pipeline.yaml` which can be used to reproduce the pipeline that generated it in distilabel using the `distilabel` CLI:

```console
distilabel pipeline run --config "https://huggingface.co/datasets/DIBT/aya_english_dpo_raw/raw/main/pipeline.yaml"
```

or explore the configuration:

```console
distilabel pipeline info --config "https://huggingface.co/datasets/DIBT/aya_english_dpo_raw/raw/main/pipeline.yaml"
```

## Dataset structure

The examples have the following structure per configuration:

<details><summary> Configuration: default </summary><hr>

```json
{
"annotation_type": "original-annotations",
"generation": "The largest organ in the human body is the skin. It covers the entire surface of the body and has a total area of about 22 square feet (2 square meters) in adults. The skin performs many important functions, such as:\n\n* Protecting the body from external damage, such as injury, infection, and UV radiation\n* Regulating body temperature\n* Aiding in the production of vitamin D\n* Assisting in the sensation of touch and feel\n* Helping to maintain fluid balance and hydration\n\nThe skin is composed of several layers, with the outermost layer being the epidermis, followed by the dermis, and then the hypodermis. It is estimated that the skin accounts for about 15% of an adult\u0027s total body weight.\n\nIt\u0027s worth noting that while the skin is the largest organ by surface area, the liver is often considered the largest organ by mass, weighing around 3 pounds (1.4 kilograms) in adults.",
"generation_model": "meta-llama/Meta-Llama-3-70B-Instruct",
"generation_models": [
"aya",
"meta-llama/Meta-Llama-3-70B-Instruct"
],
"generations": [
"The largest organ in the human body is the skin. It is the body\u0027s largest organ by surface area and weight. The skin serves many essential functions, including protecting the body from physical damage, pathogens, and dehydration, as well as helping to regulate body temperature and producing vitamin D in response to sunlight. It\u0027s a complex organ with multiple layers, cells, and structures, each serving a unique purpose in maintaining the body\u0027s overall health and well-being.",
"The largest organ in the human body is the skin. It covers the entire surface of the body and has a total area of about 22 square feet (2 square meters) in adults. The skin performs many important functions, such as:\n\n* Protecting the body from external damage, such as injury, infection, and UV radiation\n* Regulating body temperature\n* Aiding in the production of vitamin D\n* Assisting in the sensation of touch and feel\n* Helping to maintain fluid balance and hydration\n\nThe skin is composed of several layers, with the outermost layer being the epidermis, followed by the dermis, and then the hypodermis. It is estimated that the skin accounts for about 15% of an adult\u0027s total body weight.\n\nIt\u0027s worth noting that while the skin is the largest organ by surface area, the liver is often considered the largest organ by mass, weighing around 3 pounds (1.4 kilograms) in adults."
],
"instruction": "What is the largest organ in the human body?",
"language": "English",
"language_code": "eng",
"model_name": "meta-llama/Meta-Llama-3-70B-Instruct",
"predicted_generation_language": "eng_Latn",
"predicted_generation_language_score": 0.9590950012207031,
"ratings": [
5,
5
],
"rationales": [
"The text is accurate, informative, and comprehensive in describing the skin as the largest organ in the human body. It provides specific details about its functions, structure, and importance, aligning perfectly with the instruction.",
"This text is equally excellent, providing a clear and concise answer to the question. It lists the skin\u0027s functions, describes its composition, and offers additional interesting facts, such as the comparison with the liver\u0027s mass. The text is well-structured, accurate, and confident in its information, making it an excellent response."
],
"targets": "The largest organ in the human body is the skin. It is the body\u0027s largest organ by surface area and weight. The skin serves many essential functions, including protecting the body from physical damage, pathogens, and dehydration, as well as helping to regulate body temperature and producing vitamin D in response to sunlight. It\u0027s a complex organ with multiple layers, cells, and structures, each serving a unique purpose in maintaining the body\u0027s overall health and well-being.",
"user_id": "29f22cf193a81e1a5c47d76af453a91b3cd19aa348995c7add1df15fe24e8801"
}
```

This subset can be loaded as:

```python
from datasets import load_dataset

ds = load_dataset("DIBT/aya_english_dpo_raw", "default")
```

Or simply as it follows, since there's only one configuration and is named `default`:

```python
from datasets import load_dataset

ds = load_dataset("DIBT/aya_english_dpo_raw")
```

</details>

原始信息汇总

数据集概述

数据集基本信息

• 数据集名称: aya_english_dpo_raw
• 数据集大小:
  • 下载大小: 320089字节
  • 数据集大小: 567777字节
• 示例数量: 100 (训练集)
• 特征数量: 14

数据集特征

• 特征名称 (数据类型):
  • instruction (string)
  • targets (string)
  • language (string)
  • language_code (string)
  • annotation_type (string)
  • user_id (string)
  • generation_model (string)
  • generation (string)
  • predicted_generation_language (string)
  • predicted_generation_language_score (float64)
  • generations (sequence: string)
  • generation_models (sequence: string)
  • model_name (string)
  • ratings (sequence: int64)
  • rationales (sequence: string)

数据集结构

• 配置名称: default
• 数据文件:
  • 分割: train
  • 路径: data/train-*

数据集加载示例

python from datasets import load_dataset

ds = load_dataset("DIBT/aya_english_dpo_raw", "default")

或者，由于只有一个配置且名为default，可以直接加载： python from datasets import load_dataset

ds = load_dataset("DIBT/aya_english_dpo_raw")