Dataset Card for uplimit-synthetic-data-week-1-with-seed

This dataset has been created with distilabel.

The pipeline script was uploaded to easily reproduce the dataset: colab_kernel_launcher.py.

It can be run directly using the CLI:

distilabel pipeline run --script "https://huggingface.co/datasets/rutvima/uplimit-synthetic-data-week-1-with-seed/raw/main/colab_kernel_launcher.py"

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/rutvima/uplimit-synthetic-data-week-1-with-seed/raw/main/pipeline.yaml"

or explore the configuration:

distilabel pipeline info --config "https://huggingface.co/datasets/rutvima/uplimit-synthetic-data-week-1-with-seed/raw/main/pipeline.yaml"

Dataset structure

The examples have the following structure per configuration:

Configuration: default

---

{
    "cluster_label": 1,
    "distilabel_metadata": {
        "raw_input_text_generation_0": [
            {
                "content": "Generate an artwork of the 19th-century American painting style for a hypothetical salon in Cincinnati, incorporating elements of the city\u0027s local cultural heritage, such as a painting including views of the Ohio River or significant historical landmarks. Research the influence of the American Impressionist movement on Cincinnati\u0027s local art scene during the late 19th century. Compare and contrast the contrasting styles of Thomas Cole and Winslow Homer in their depictions of 19th-century American landscapes. Explain the role of Cincinnati\u0027s German-American influence on the American art movement, including notable artists such as Albert Bierstadt. Create a recipe inspired by traditional Cincinnati culinary practices",
                "role": "user"
            }
        ],
        "raw_output_text_generation_0": "Title: \"Riverfront Reverie: A Salon in Cincinnati\"\n\nIn the late 19th century, Cincinnati\u0027s artistic scene was heavily influenced by the American Impressionist movement, which emphasized capturing light and color in outdoor settings. Our artwork, \"Riverfront Reverie: A Salon in Cincinnati,\" is a syncretic piece that combines elements of Cincinnati\u0027s cultural heritage with the Impressionist spirit.\n\nDescription:\n\nThe painting depicts a serene scene of the Ohio River, with the Cincinnati skyline in the background. The river itself is a symbol of the city\u0027s economic and industrial growth, while the skyline represents the city\u0027s rich history and cultural",
        "statistics_text_generation_0": {
            "input_tokens": 162,
            "output_tokens": 128
        }
    },
    "embedding": [
        0.022470641881227493,
        -0.017901265993714333,
        -0.011149224825203419,
        -0.009838403202593327,
        0.06471165269613266,
        0.0012222680961713195,
        -0.008083968423306942,
        0.010446570813655853,
        0.027933161705732346,
        -0.003492367221042514,
        "... (truncated - showing 10 of 1024 elements)"
    ],
    "generation": "Title: \"Riverfront Reverie: A Salon in Cincinnati\"\n\nIn the late 19th century, Cincinnati\u0027s artistic scene was heavily influenced by the American Impressionist movement, which emphasized capturing light and color in outdoor settings. Our artwork, \"Riverfront Reverie: A Salon in Cincinnati,\" is a syncretic piece that combines elements of Cincinnati\u0027s cultural heritage with the Impressionist spirit.\n\nDescription:\n\nThe painting depicts a serene scene of the Ohio River, with the Cincinnati skyline in the background. The river itself is a symbol of the city\u0027s economic and industrial growth, while the skyline represents the city\u0027s rich history and cultural",
    "id": "\u003curn:uuid:ab0a5c2f-e34c-4781-8bf8-6a3d1fd82649\u003e",
    "instructions": "Generate an artwork of the 19th-century American painting style for a hypothetical salon in Cincinnati, incorporating elements of the city\u0027s local cultural heritage, such as a painting including views of the Ohio River or significant historical landmarks. Research the influence of the American Impressionist movement on Cincinnati\u0027s local art scene during the late 19th century. Compare and contrast the contrasting styles of Thomas Cole and Winslow Homer in their depictions of 19th-century American landscapes. Explain the role of Cincinnati\u0027s German-American influence on the American art movement, including notable artists such as Albert Bierstadt. Create a recipe inspired by traditional Cincinnati culinary practices",
    "model_name": "https://api-inference.huggingface.co/models/meta-llama/Llama-3.2-3B-Instruct",
    "model_name_embeddings": "Alibaba-NLP/gte-large-en-v1.5",
    "nn_indices": [
        15125,
        37073,
        71970,
        26917,
        4480,
        69453,
        71903,
        9411,
        39149,
        59512,
        "... (truncated - showing 10 of 20 elements)"
    ],
    "nn_scores": [
        0.8340727686882019,
        0.8202860355377197,
        0.8056823015213013,
        0.8035473227500916,
        0.7944107055664062,
        0.7865492105484009,
        0.7834657430648804,
        0.7777583599090576,
        0.7766708135604858,
        0.7716180682182312,
        "... (truncated - showing 10 of 20 elements)"
    ],
    "persona": "A local art historian and museum professional interested in 19th-century American art and the local cultural heritage of Cincinnati.",
    "projection": [
        4.902285575866699,
        1.8720051050186157
    ],
    "summary_label": "[\"Education\", \"Academia\", \"Specialized Expertise\"]"
}

This subset can be loaded as:

from datasets import load_dataset

ds = load_dataset("rutvima/uplimit-synthetic-data-week-1-with-seed", "default")

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

from datasets import load_dataset

ds = load_dataset("rutvima/uplimit-synthetic-data-week-1-with-seed")

References

@misc{wang2023selfinstructaligninglanguagemodels,
    title={Self-Instruct: Aligning Language Models with Self-Generated Instructions},
    author={Yizhong Wang and Yeganeh Kordi and Swaroop Mishra and Alisa Liu and Noah A. Smith and Daniel Khashabi and Hannaneh Hajishirzi},
    year={2023},
    eprint={2212.10560},
    archivePrefix={arXiv},
    primaryClass={cs.CL},
    url={https://arxiv.org/abs/2212.10560},
}