README.md

metadata

size_categories: n<1K
dataset_info:
  features:
    - name: instruction
      dtype: string
    - name: generation
      dtype: 'null'
    - name: distilabel_metadata
      struct:
        - name: raw_input_text_generation_0
          list:
            - name: content
              dtype: string
            - name: role
              dtype: string
        - name: raw_output_text_generation_0
          dtype: 'null'
    - name: model_name
      dtype: string
  splits:
    - name: train
      num_bytes: 8124
      num_examples: 10
  download_size: 9365
  dataset_size: 8124
configs:
  - config_name: default
    data_files:
      - split: train
        path: data/train-*
tags:
  - synthetic
  - distilabel
  - rlaif

Dataset Card for mydataset9

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/OlegToshchev/mydataset9/raw/main/pipeline.yaml"

or explore the configuration:

distilabel pipeline info --config "https://huggingface.co/datasets/OlegToshchev/mydataset9/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": null
    },
    "generation": null,
    "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": "http://localhost:8000/"
}

This subset can be loaded as:

from datasets import load_dataset

ds = load_dataset("OlegToshchev/mydataset9", "default")

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

from datasets import load_dataset

ds = load_dataset("OlegToshchev/mydataset9")