Dataset Card for uplimit-demo-synthetic-data-week-1-basic

This dataset has been created with distilabel.

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:

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

or explore the configuration:

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

Dataset structure

The examples have the following structure per configuration:

Configuration: default

---

{
    "distilabel_metadata": {
        "raw_input_text_generation_1": [
            {
                "content": "Here\u0027s a short question about CNN:\n\nWhat year was the Cable News Network (CNN) launched, revolutionizing the way people consume news and information?",
                "role": "user"
            }
        ],
        "raw_output_text_generation_1": "CNN, the Cable News Network, was launched in 1980.",
        "statistics_text_generation_1": {
            "input_tokens": 65,
            "output_tokens": 15
        }
    },
    "instruction": "Here\u0027s a short question about CNN:\n\nWhat year was the Cable News Network (CNN) launched, revolutionizing the way people consume news and information?",
    "model_name": "https://api-inference.huggingface.co/models/meta-llama/Llama-3.2-3B-Instruct",
    "response": "CNN, the Cable News Network, was launched in 1980."
}

This subset can be loaded as:

from datasets import load_dataset

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

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

from datasets import load_dataset

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