Dataset Card for test-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/ze00ro/test-dataset/raw/main/pipeline.yaml"

or explore the configuration:

distilabel pipeline info --config "https://huggingface.co/datasets/ze00ro/test-dataset/raw/main/pipeline.yaml"

Dataset structure

The examples have the following structure per configuration:

Configuration: default

---

{
    "distilabel_metadata": {
        "raw_input_text_generation_with_qwen25": [
            {
                "content": "You are an exam writer specialized in writing exams for students.\nYour goal is to create questions and answers based on the document provided, and a list of distractors, that are incorrect but viable answers to the question.\nYour answer must adhere to the following format:\n```\n[\n    {\n        \"question\": \"Your question\",\n        \"answer\": \"The correct answer to the question\"\n    },\n    ... (more questions and answers as required)\n]\n```",
                "role": "system"
            },
            {
                "content": "Generate a list of answers and questions about the document. Document:\n\nWhat are 2+2?",
                "role": "user"
            }
        ],
        "raw_output_text_generation_with_qwen25": "[\n    {\n        \"question\": \"What is the sum of 2+2?\",\n        \"answer\": \"4\"\n    }\n] \n\nNote: Since the provided document is very brief, the question generated is straightforward without additional distractors. The format requested was for questions and answers only, not multiple-choice with distractors.",
        "statistics_text_generation_with_qwen25": {
            "input_tokens": 124,
            "output_tokens": 67
        }
    },
    "document": "What are 2+2?",
    "generations": [
        "[\n    {\n        \"question\": \"What is the sum of 2+2?\",\n        \"answer\": \"4\"\n    }\n] \n\nNote: Since the provided document is very brief, the question generated is straightforward without additional distractors. The format requested was for questions and answers only, not multiple-choice with distractors."
    ],
    "model_names": [
        "qwen2.5:32b"
    ]
}

This subset can be loaded as:

from datasets import load_dataset

ds = load_dataset("ze00ro/test-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("ze00ro/test-dataset")