Dataset Card for synthetic1

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/tofuminx/synthetic1/raw/main/pipeline.yaml"

or explore the configuration:

distilabel pipeline info --config "https://huggingface.co/datasets/tofuminx/synthetic1/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                "content": "What is the maximum amount of money that can be withdrawn from an ATM in one transaction?",
                "role": "user"
            }
        ],
        "raw_output_text_generation_1": "The maximum amount of money that can be withdrawn from an ATM in one transaction varies depending on the bank and the type of ATM. In general, it\u0027s typically between $500 to $1,000 per transaction. However, some banks may have higher limits for certain types of accounts or for specific ATMs. It\u0027s always best to check with your bank directly for their specific policies.",
        "statistics_text_generation_1": {
            "input_tokens": 18,
            "output_tokens": 81
        }
    },
    "instruction": "What is the maximum amount of money that can be withdrawn from an ATM in one transaction?",
    "model_name": "HuggingFaceTB/SmolLM2-1.7B-Instruct",
    "response": "The maximum amount of money that can be withdrawn from an ATM in one transaction varies depending on the bank and the type of ATM. In general, it\u0027s typically between $500 to $1,000 per transaction. However, some banks may have higher limits for certain types of accounts or for specific ATMs. It\u0027s always best to check with your bank directly for their specific policies."
}

This subset can be loaded as:

from datasets import load_dataset

ds = load_dataset("tofuminx/synthetic1", "default")

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

from datasets import load_dataset

ds = load_dataset("tofuminx/synthetic1")