README.md

metadata

size_categories: n<1K
dataset_info:
  features:
    - name: instruction
      dtype: string
    - name: generation
      dtype: string
    - name: distilabel_metadata
      struct:
        - name: raw_output_text_generation_0
          dtype: string
        - name: raw_input_text_generation_0
          list:
            - name: role
              dtype: string
            - name: content
              dtype: string
        - name: statistics_text_generation_0
          struct:
            - name: input_tokens
              dtype: int64
            - name: output_tokens
              dtype: int64
    - name: model_name
      dtype: string
  splits:
    - name: train
      num_bytes: 32848
      num_examples: 10
  download_size: 40020
  dataset_size: 32848
configs:
  - config_name: default
    data_files:
      - split: train
        path: data/train-*
tags:
  - synthetic
  - distilabel
  - rlaif

Dataset Card for distilabel-example

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/davidmeikle/distilabel-example/raw/main/pipeline.yaml"

or explore the configuration:

distilabel pipeline info --config "https://huggingface.co/datasets/davidmeikle/distilabel-example/raw/main/pipeline.yaml"

Dataset structure

The examples have the following structure per configuration:

Configuration: default

---

{
    "distilabel_metadata": {
        "raw_input_text_generation_0": [
            {
                "content": "Arianna has 12 chocolates more than Danny. Danny has 6 chocolates more than Robbie. Arianna has twice as many chocolates as Robbie has. How many chocolates does Danny have?",
                "role": "user"
            }
        ],
        "raw_output_text_generation_0": "To solve this problem, let\u0027s break it down step by step.\n\n1. Let\u0027s say Robbie has \u0027x\u0027 chocolates.\n\n2. Danny has 6 chocolates more than Robbie, so Danny has \u0027x + 6\u0027 chocolates.\n\n3. Arianna has 12 chocolates more than Danny, so Arianna has \u0027x + 6 + 12\u0027 chocolates. This can be simplified to \u0027x + 18\u0027 chocolates.\n\n4. Arianna has twice as many chocolates as Robbie, so we can set up the equation: x + 18 = 2x.\n\n5. Now, let\u0027s solve for \u0027x\u0027. Subtract \u0027x\u0027 from both sides: 18 = x. \n\n6. Now that we know Robbie has 18 chocolates, and Danny has 6 chocolates more than Robbie, we can find the number of chocolates Danny has by substituting \u0027x\u0027 into the equation \u0027x + 6\u0027: 18 + 6 = 24.\n\nSo, Danny has 24 chocolates.",
        "statistics_text_generation_0": {
            "input_tokens": 73,
            "output_tokens": 206
        }
    },
    "generation": "To solve this problem, let\u0027s break it down step by step.\n\n1. Let\u0027s say Robbie has \u0027x\u0027 chocolates.\n\n2. Danny has 6 chocolates more than Robbie, so Danny has \u0027x + 6\u0027 chocolates.\n\n3. Arianna has 12 chocolates more than Danny, so Arianna has \u0027x + 6 + 12\u0027 chocolates. This can be simplified to \u0027x + 18\u0027 chocolates.\n\n4. Arianna has twice as many chocolates as Robbie, so we can set up the equation: x + 18 = 2x.\n\n5. Now, let\u0027s solve for \u0027x\u0027. Subtract \u0027x\u0027 from both sides: 18 = x. \n\n6. Now that we know Robbie has 18 chocolates, and Danny has 6 chocolates more than Robbie, we can find the number of chocolates Danny has by substituting \u0027x\u0027 into the equation \u0027x + 6\u0027: 18 + 6 = 24.\n\nSo, Danny has 24 chocolates.",
    "instruction": "Arianna has 12 chocolates more than Danny. Danny has 6 chocolates more than Robbie. Arianna has twice as many chocolates as Robbie has. How many chocolates does Danny have?",
    "model_name": "meta-llama/Llama-3.1-8B-Instruct"
}

This subset can be loaded as:

from datasets import load_dataset

ds = load_dataset("davidmeikle/distilabel-example", "default")

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

from datasets import load_dataset

ds = load_dataset("davidmeikle/distilabel-example")