---
size_categories: n<1K
dataset_info:
  features:
  - name: instruction
    dtype: string
  - name: distilabel_metadata
    struct:
    - name: raw_input_text_generation_1
      list:
      - name: content
        dtype: string
      - name: role
        dtype: string
    - name: raw_output_text_generation_1
      dtype: string
    - name: statistics_text_generation_1
      struct:
      - name: input_tokens
        dtype: int64
      - name: output_tokens
        dtype: int64
  - name: model_name
    dtype: string
  - name: response
    dtype: string
  splits:
  - name: train
    num_bytes: 1574
    num_examples: 1
  download_size: 11843
  dataset_size: 1574
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 uplimit-synthetic-data-week-1-basic

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/uonyeka/uplimit-synthetic-data-week-1-basic/raw/main/pipeline.yaml"
```

or explore the configuration:

```console
distilabel pipeline info --config "https://huggingface.co/datasets/uonyeka/uplimit-synthetic-data-week-1-basic/raw/main/pipeline.yaml"
```

## Dataset structure

The examples have the following structure per configuration:


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

```json
{
    "distilabel_metadata": {
        "raw_input_text_generation_1": [
            {
                "content": "What is the competition level between Cable News Network (CNN) and its rival, Fox News Channel, in terms of ratings and viewership?",
                "role": "user"
            }
        ],
        "raw_output_text_generation_1": "The competition level between CNN and Fox News Channel (FNC) is a long-standing and highly competitive one, particularly in the United States. Both networks have a significant following and are known for their lively and opinion-driven programming. Here\u0027s an overview of their ratings and viewership:\n\n**Ratings:**\n\n1. Primetime ratings: According to Nielsen Media Research, the prime-time ratings for CNN and FNC have fluctuated over the years. In recent years (2020-2022), FNC generally has a slight edge over CNN in primetime, with an average audience of around 890,000 viewers per night.\n2.",
        "statistics_text_generation_1": {
            "input_tokens": 63,
            "output_tokens": 128
        }
    },
    "instruction": "What is the competition level between Cable News Network (CNN) and its rival, Fox News Channel, in terms of ratings and viewership?",
    "model_name": "https://api-inference.huggingface.co/models/meta-llama/Llama-3.2-3B-Instruct",
    "response": "The competition level between CNN and Fox News Channel (FNC) is a long-standing and highly competitive one, particularly in the United States. Both networks have a significant following and are known for their lively and opinion-driven programming. Here\u0027s an overview of their ratings and viewership:\n\n**Ratings:**\n\n1. Primetime ratings: According to Nielsen Media Research, the prime-time ratings for CNN and FNC have fluctuated over the years. In recent years (2020-2022), FNC generally has a slight edge over CNN in primetime, with an average audience of around 890,000 viewers per night.\n2."
}
```

This subset can be loaded as:

```python
from datasets import load_dataset

ds = load_dataset("uonyeka/uplimit-synthetic-data-week-1-basic", "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("uonyeka/uplimit-synthetic-data-week-1-basic")
```


</details>