test / README.md
do11's picture
Upload README.md with huggingface_hub
72bf194
|
raw
history blame
10.2 kB
metadata
size_categories: 10K<n<100K
tags:
  - rlfh
  - argilla
  - human-feedback

Dataset Card for test

This dataset has been created with Argilla.

As shown in the sections below, this dataset can be loaded into Argilla as explained in Load with Argilla, or used directly with the datasets library in Load with datasets.

Dataset Description

Dataset Summary

This dataset contains:

  • A dataset configuration file conforming to the Argilla dataset format named argilla.cfg. This configuration file will be used to configure the dataset when using the FeedbackDataset.from_huggingface method in Argilla.

  • Dataset records in a format compatible with HuggingFace datasets. These records will be loaded automatically when using FeedbackDataset.from_huggingface and can be loaded independently using the datasets library via load_dataset.

  • The annotation guidelines that have been used for building and curating the dataset, if they've been defined in Argilla.

Load with Argilla

To load with Argilla, you'll just need to install Argilla as pip install argilla --upgrade and then use the following code:

import argilla as rg

ds = rg.FeedbackDataset.from_huggingface("do11/test")

Load with datasets

To load this dataset with datasets, you'll just need to install datasets as pip install datasets --upgrade and then use the following code:

from datasets import load_dataset

ds = load_dataset("do11/test")

Supported Tasks and Leaderboards

This dataset can contain multiple fields, questions and responses so it can be used for different NLP tasks, depending on the configuration. The dataset structure is described in the Dataset Structure section.

There are no leaderboards associated with this dataset.

Languages

[More Information Needed]

Dataset Structure

Data in Argilla

The dataset is created in Argilla with: fields, questions, and guidelines.

The fields are the dataset records themselves, for the moment just text fields are suppported. These are the ones that will be used to provide responses to the questions.

Field Name Title Type Required Markdown
category Task category TextField True False
instruction Instruction TextField True False
context Input TextField True False
response Response TextField True False

The questions are the questions that will be asked to the annotators. They can be of different types, such as rating, text, single choice, or multiple choice.

Question Name Title Type Required Description Values/Labels
new-instruction Final instruction: TextQuestion True Write the final version of the instruction, making sure that it matches the task category. If the original instruction is ok, copy and paste it here. N/A
new-input Final input: TextQuestion True Write the final version of the input, making sure that it makes sense with the task category. If the original input is ok, copy and paste it here. If an input is not needed, leave this empty. N/A
new-response Final response: TextQuestion True Write the final version of the response, making sure that it matches the task category and makes sense for the instruction (and input) provided. If the original response is ok, copy and paste it here. N/A

Finally, the guidelines are just a plain string that can be used to provide instructions to the annotators. Find those in the annotation guidelines section.

Data Instances

An example of a dataset instance in Argilla looks as follows:

{
    "external_id": "0",
    "fields": {
        "category": "closed_qa",
        "context": "Virgin Australia, the trading name of Virgin Australia Airlines Pty Ltd, is an Australian-based airline. It is the largest airline by fleet size to use the Virgin brand. It commenced services on 31 August 2000 as Virgin Blue, with two aircraft on a single route. It suddenly found itself as a major airline in Australia\u0027s domestic market after the collapse of Ansett Australia in September 2001. The airline has since grown to directly serve 32 cities in Australia, from hubs in Brisbane, Melbourne and Sydney.",
        "instruction": "When did Virgin Australia start operating?",
        "response": "Virgin Australia commenced services on 31 August 2000 as Virgin Blue, with two aircraft on a single route."
    },
    "metadata": null,
    "responses": []
}

While the same record in HuggingFace datasets looks as follows:

{
    "category": "closed_qa",
    "context": "Virgin Australia, the trading name of Virgin Australia Airlines Pty Ltd, is an Australian-based airline. It is the largest airline by fleet size to use the Virgin brand. It commenced services on 31 August 2000 as Virgin Blue, with two aircraft on a single route. It suddenly found itself as a major airline in Australia\u0027s domestic market after the collapse of Ansett Australia in September 2001. The airline has since grown to directly serve 32 cities in Australia, from hubs in Brisbane, Melbourne and Sydney.",
    "external_id": "0",
    "instruction": "When did Virgin Australia start operating?",
    "metadata": null,
    "new-input": null,
    "new-instruction": null,
    "new-response": null,
    "response": "Virgin Australia commenced services on 31 August 2000 as Virgin Blue, with two aircraft on a single route."
}

Data Fields

Among the dataset fields, we differentiate between the following:

  • Fields: These are the dataset records themselves, for the moment just text fields are suppported. These are the ones that will be used to provide responses to the questions.

    • category is of type TextField.
    • instruction is of type TextField.
    • (optional) context is of type TextField.
    • response is of type TextField.
  • Questions: These are the questions that will be asked to the annotators. They can be of different types, such as rating, text, single choice, or multiple choice.

    • new-instruction is of type TextQuestion, and description "Write the final version of the instruction, making sure that it matches the task category. If the original instruction is ok, copy and paste it here.".
    • (optional) new-input is of type TextQuestion, and description "Write the final version of the input, making sure that it makes sense with the task category. If the original input is ok, copy and paste it here. If an input is not needed, leave this empty.".
    • new-response is of type TextQuestion, and description "Write the final version of the response, making sure that it matches the task category and makes sense for the instruction (and input) provided. If the original response is ok, copy and paste it here.".

Additionally, we also have one more field which is optional and is the following:

  • external_id: This is an optional field that can be used to provide an external ID for the dataset record. This can be useful if you want to link the dataset record to an external resource, such as a database or a file.

Data Splits

The dataset contains a single split, which is train.

Dataset Creation

Curation Rationale

[More Information Needed]

Source Data

Initial Data Collection and Normalization

[More Information Needed]

Who are the source language producers?

[More Information Needed]

Annotations

Annotation guidelines

In this dataset, you will find a collection of records that show a category, an instruction, an input and a response to that instruction. The aim of the project is to correct the instructions, intput and responses to make sure they are of the highest quality and that they match the task category that they belong to. All three texts should be clear and include real information. In addition, the response should be as complete but concise as possible.

To curate the dataset, you will need to provide an answer to the following text fields:

1 - Final instruction: The final version of the instruction field. You may copy it using the copy icon in the instruction field. Leave it as it is if it's ok or apply any necessary corrections. Remember to change the instruction if it doesn't represent well the task category of the record.

2 - Final input: The final version of the instruction field. You may copy it using the copy icon in the input field. Leave it as it is if it's ok or apply any necessary corrections. If the task category and instruction don't need of an input to be completed, leave this question blank.

3 - Final response: The final version of the response field. You may copy it using the copy icon in the response field. Leave it as it is if it's ok or apply any necessary corrections. Check that the response makes sense given all the fields above.

You will need to provide at least an instruction and a response for all records. If you are not sure about a record and you prefer not to provide a response, click Discard.

Annotation process

[More Information Needed]

Who are the annotators?

[More Information Needed]

Personal and Sensitive Information

[More Information Needed]

Considerations for Using the Data

Social Impact of Dataset

[More Information Needed]

Discussion of Biases

[More Information Needed]

Other Known Limitations

[More Information Needed]

Additional Information

Dataset Curators

[More Information Needed]

Licensing Information

[More Information Needed]

Citation Information

[More Information Needed]

Contributions

[More Information Needed]