Dataset Card for uplimit-instruction-tuning-dataset

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/johnmccabe/uplimit-instruction-tuning-dataset/raw/main/pipeline.yaml"

or explore the configuration:

distilabel pipeline info --config "https://huggingface.co/datasets/johnmccabe/uplimit-instruction-tuning-dataset/raw/main/pipeline.yaml"

Dataset structure

The examples have the following structure per configuration:

Configuration: default

---

{
    "distilabel_metadata": {
        "raw_input_text_generation_1": [
            {
                "content": "What is the name of the platform that allows users to purchase and sell digital content such as music, movies, and games?",
                "role": "user"
            }
        ],
        "raw_output_text_generation_1": "The platform you\u0027re referring to is called \"Steam\". It\u0027s an online marketplace for video games. However, if you\u0027re looking for platforms where people can buy and sell digital content like music or movies, some popular options include Audible (for audiobooks), iTunes (for music and movies), and Amazon Marketplace (for various types of digital goods).",
        "statistics_text_generation_1": {
            "input_tokens": 25,
            "output_tokens": 74
        }
    },
    "instruction": "What is the name of the platform that allows users to purchase and sell digital content such as music, movies, and games?",
    "model_name": "HuggingFaceTB/SmolLM2-1.7B-Instruct",
    "response": "The platform you\u0027re referring to is called \"Steam\". It\u0027s an online marketplace for video games. However, if you\u0027re looking for platforms where people can buy and sell digital content like music or movies, some popular options include Audible (for audiobooks), iTunes (for music and movies), and Amazon Marketplace (for various types of digital goods)."
}

This subset can be loaded as:

from datasets import load_dataset

ds = load_dataset("johnmccabe/uplimit-instruction-tuning-dataset", "default")

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

from datasets import load_dataset

ds = load_dataset("johnmccabe/uplimit-instruction-tuning-dataset")