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

or explore the configuration:

distilabel pipeline info --config "https://huggingface.co/datasets/Tiamz/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_self_instruct_0": [
            {
                "content": "# Task Description\nDevelop 5 user queries that can be received by the given AI application and applicable to the provided context. Emphasize diversity in verbs and linguistic structures within the model\u0027s textual capabilities.\n\n# Criteria for Queries\nIncorporate a diverse range of verbs, avoiding repetition.\nEnsure queries are compatible with AI model\u0027s text generation functions and are limited to 1-2 sentences.\nDesign queries to be self-contained and standalone.\nBlend interrogative (e.g., \"What is the significance of x?\") and imperative (e.g., \"Detail the process of x.\") styles.\nWrite each query on a separate line and avoid using numbered lists or bullet points.\n\n# AI Application\nAI assistant\n\n# Context\nA local art historian and museum professional interested in 19th-century American art and the local cultural heritage of Cincinnati.\n\n# Output\n",
                "role": "user"
            }
        ],
        "raw_input_text_generation_0": null,
        "raw_output_self_instruct_0": "Write a comprehensive history of the Cincinnati Art Museum\u0027s collection of 19th-century American art, highlighting its most notable pieces and their cultural significance.\n\nProvide a detailed analysis of the artistic style of Frederic Edwin Church, specifically focusing on his landscape paintings and their influence on American art during the 19th century.\n\nWhat were the primary motivations behind the establishment of the Cincinnati Museum Center at Union Terminal, and how has it contributed to the preservation of local cultural heritage?\n\nWould it be possible to curate an exhibition featuring the works of 19th-century American artists who were influenced by the Cincinnati art scene, and what would be the main themes and",
        "raw_output_text_generation_0": null,
        "statistics_self_instruct_0": {
            "input_tokens": 205,
            "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": null,
    "id": "\u003curn:uuid:ab0a5c2f-e34c-4781-8bf8-6a3d1fd82649\u003e",
    "instructions": [
        "Write a comprehensive history of the Cincinnati Art Museum\u0027s collection of 19th-century American art, highlighting its most notable pieces and their cultural significance.",
        "Provide a detailed analysis of the artistic style of Frederic Edwin Church, specifically focusing on his landscape paintings and their influence on American art during the 19th century.",
        "What were the primary motivations behind the establishment of the Cincinnati Museum Center at Union Terminal, and how has it contributed to the preservation of local cultural heritage?",
        "Would it be possible to curate an exhibition featuring the works of 19th-century American artists who were influenced by the Cincinnati art scene, and what would be the main themes and"
    ],
    "model_name": null,
    "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("Tiamz/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("Tiamz/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},
}