File size: 3,879 Bytes
f43a87a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
---

size_categories: n<1K
dataset_info:
  features:
  - name: instruction
    dtype: string
  - name: generation
    dtype: string
  - 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: 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: 17686
    num_examples: 10
  download_size: 22060
  dataset_size: 17686
configs:
- config_name: default
  data_files:
  - split: train
    path: data/train-*
tags:
- synthetic
- distilabel
- rlaif
---


<p align="left">
  <a href="https://github.com/argilla-io/distilabel">
    <img src="https://raw.githubusercontent.com/argilla-io/distilabel/main/docs/assets/distilabel-badge-light.png" alt="Built with Distilabel" width="200" height="32"/>

  </a>

</p>


# Dataset Card for distilabel-example

This dataset has been created with [distilabel](https://distilabel.argilla.io/).



## 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:

```console

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

```

or explore the configuration:

```console

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

```

## Dataset structure

The examples have the following structure per configuration:


<details><summary> Configuration: default </summary><hr>

```json

{

    "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": "Let the number of chocolates Robbie has be \\( r \\).\n\nFrom the problem, we know:\n\n1. Danny has 6 chocolates more than Robbie:\n   \\[\n   d = r + 6\n   \\]\n\n2. Arianna has 12 chocolates more than Danny:\n   \\[\n   a = d + 12\n   \\]\n\n3. Arianna has twice as many chocolates as Robbie:\n   \\[\n   a = 2r\n   \\]\n\nWe can now substitute \\( d \\) into the equation for \\( a \\):\n\\[\na = (r + 6) + 12\n\\]\nThis",

        "statistics_text_generation_0": {

            "input_tokens": 45,

            "output_tokens": 128

        }

    },

    "generation": "Let the number of chocolates Robbie has be \\( r \\).\n\nFrom the problem, we know:\n\n1. Danny has 6 chocolates more than Robbie:\n   \\[\n   d = r + 6\n   \\]\n\n2. Arianna has 12 chocolates more than Danny:\n   \\[\n   a = d + 12\n   \\]\n\n3. Arianna has twice as many chocolates as Robbie:\n   \\[\n   a = 2r\n   \\]\n\nWe can now substitute \\( d \\) into the equation for \\( a \\):\n\\[\na = (r + 6) + 12\n\\]\nThis",

    "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": "gpt-4o-mini"

}

```

This subset can be loaded as:

```python

from datasets import load_dataset



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

```

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

```python

from datasets import load_dataset



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

```


</details>