---
size_categories: 1K<n<10K
tags:
- rlfh
- argilla
- human-feedback
---
# Dataset Card for sharegpt-text-descriptives
This dataset has been created with [Argilla](https://docs.argilla.io).
As shown in the sections below, this dataset can be loaded into Argilla as explained in [Load with Argilla](#load-with-argilla), or used directly with the `datasets` library in [Load with `datasets`](#load-with-datasets).
## Dataset Description
- **Homepage:** https://argilla.io
- **Repository:** https://github.com/argilla-io/argilla
- **Paper:**
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
This dataset contains:
* A dataset configuration file conforming to the Argilla dataset format named `argilla.yaml`. 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](#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:
```python
import argilla as rg
ds = rg.FeedbackDataset.from_huggingface("argilla/sharegpt-text-descriptives")
```
### 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:
```python
from datasets import load_dataset
ds = load_dataset("argilla/sharegpt-text-descriptives")
```
### Supported Tasks and Leaderboards
This dataset can contain [multiple fields, questions and responses](https://docs.argilla.io/en/latest/conceptual_guides/data_model.html#feedback-dataset) so it can be used for different NLP tasks, depending on the configuration. The dataset structure is described in the [Dataset Structure section](#dataset-structure).
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**, **suggestions**, **metadata**, and **guidelines**.
The **fields** are the dataset records themselves, for the moment just text fields are supported. These are the ones that will be used to provide responses to the questions.
| Field Name | Title | Type | Required | Markdown |
| ---------- | ----- | ---- | -------- | -------- |
| prompt | Prompt | text | True | True |
| context | Context | text | False | True |
The **questions** are the questions that will be asked to the annotators. They can be of different types, such as rating, text, label_selection, multi_label_selection, or ranking.
| Question Name | Title | Type | Required | Description | Values/Labels |
| ------------- | ----- | ---- | -------- | ----------- | ------------- |
| response | Response | text | True | Write the response to the instruction. | N/A |
The **suggestions** are human or machine generated recommendations for each question to assist the annotator during the annotation process, so those are always linked to the existing questions, and named appending "-suggestion" and "-suggestion-metadata" to those, containing the value/s of the suggestion and its metadata, respectively. So on, the possible values are the same as in the table above, but the column name is appended with "-suggestion" and the metadata is appended with "-suggestion-metadata".
**✨ NEW** The **metadata** is a dictionary that can be used to provide additional information about the dataset record. This can be useful to provide additional context to the annotators, or to provide additional information about the dataset record itself. For example, you can use this to provide a link to the original source of the dataset record, or to provide additional information about the dataset record itself, such as the author, the date, or the source. The metadata is always optional, and can be potentially linked to the `metadata_properties` defined in the dataset configuration file in `argilla.yaml`.
The **guidelines**, are optional as well, and are just a plain string that can be used to provide instructions to the annotators. Find those in the [annotation guidelines](#annotation-guidelines) section.
### Data Instances
An example of a dataset instance in Argilla looks as follows:
```json
{
"external_id": null,
"fields": {
"prompt": "How to tell if a customer segment is well segmented? In 3 bullet points."
},
"metadata": {
"prompt_alpha_ratio": 0.8125,
"prompt_automated_readability_index": 1.24642857142857,
"prompt_coleman_liau_index": 3.9114285714285693,
"prompt_dependency_distance_mean": 2.3181818181818183,
"prompt_dependency_distance_std": 0.3181818181818181,
"prompt_doc_length": 16.0,
"prompt_duplicate_line_chr_fraction": 0.0,
"prompt_duplicate_ngram_chr_fraction_10": 0.0,
"prompt_duplicate_ngram_chr_fraction_5": 0.0,
"prompt_duplicate_ngram_chr_fraction_6": 0.0,
"prompt_duplicate_ngram_chr_fraction_7": 0.0,
"prompt_duplicate_ngram_chr_fraction_8": 0.0,
"prompt_duplicate_ngram_chr_fraction_9": 0.0,
"prompt_duplicate_paragraph_chr_fraction": 0.0,
"prompt_entropy": 0.4249943780917443,
"prompt_flesch_kincaid_grade": 3.997142857142858,
"prompt_flesch_reading_ease": 78.87285714285717,
"prompt_gunning_fog": 8.514285714285714,
"prompt_lix": 28.428571428571427,
"prompt_mean_word_length": 3.6875,
"prompt_n_characters": 59,
"prompt_n_sentences": 2,
"prompt_n_stop_words": 7.0,
"prompt_n_tokens": 14,
"prompt_n_unique_tokens": 14,
"prompt_oov_ratio": 0.0,
"prompt_passed_quality_check": "True",
"prompt_per_word_perplexity": 0.0955988637794089,
"prompt_perplexity": 1.5295818204705425,
"prompt_pos_prop_ADJ": 0.0,
"prompt_pos_prop_ADP": 0.0625,
"prompt_pos_prop_ADV": 0.0625,
"prompt_pos_prop_AUX": 0.0625,
"prompt_pos_prop_CCONJ": 0.0,
"prompt_pos_prop_DET": 0.0625,
"prompt_pos_prop_INTJ": 0.0,
"prompt_pos_prop_NOUN": 0.25,
"prompt_pos_prop_NUM": 0.0625,
"prompt_pos_prop_PART": 0.0625,
"prompt_pos_prop_PRON": 0.0,
"prompt_pos_prop_PROPN": 0.0,
"prompt_pos_prop_PUNCT": 0.125,
"prompt_pos_prop_SCONJ": 0.125,
"prompt_pos_prop_SYM": 0.0,
"prompt_pos_prop_VERB": 0.125,
"prompt_pos_prop_X": 0.0,
"prompt_prop_adjacent_dependency_relation_mean": 0.28181818181818186,
"prompt_prop_adjacent_dependency_relation_std": 0.08181818181818182,
"prompt_proportion_bullet_points": 0.0,
"prompt_proportion_ellipsis": 0.0,
"prompt_proportion_unique_tokens": 1.0,
"prompt_rix": 1.5,
"prompt_sentence_length_mean": 7.0,
"prompt_sentence_length_median": 7.0,
"prompt_sentence_length_std": 3.0,
"prompt_syllables_per_token_mean": 1.4285714285714286,
"prompt_syllables_per_token_median": 1.0,
"prompt_syllables_per_token_std": 0.7284313590846836,
"prompt_symbol_to_word_ratio_#": 0.0,
"prompt_token_length_mean": 4.071428571428571,
"prompt_token_length_median": 3.5,
"prompt_token_length_std": 2.5763841138387766,
"prompt_top_ngram_chr_fraction_2": 0.0,
"prompt_top_ngram_chr_fraction_3": 0.0,
"prompt_top_ngram_chr_fraction_4": 0.0,
"response_alpha_ratio": 0.7857142857142857,
"response_automated_readability_index": 11.4375,
"response_coleman_liau_index": 16.030000000000005,
"response_dependency_distance_mean": 2.0984405458089666,
"response_dependency_distance_std": 1.2368394170758057,
"response_doc_length": 70.0,
"response_duplicate_line_chr_fraction": 0.0,
"response_duplicate_ngram_chr_fraction_10": 0.0,
"response_duplicate_ngram_chr_fraction_5": 0.14761904761904762,
"response_duplicate_ngram_chr_fraction_6": 0.0,
"response_duplicate_ngram_chr_fraction_7": 0.0,
"response_duplicate_ngram_chr_fraction_8": 0.0,
"response_duplicate_ngram_chr_fraction_9": 0.0,
"response_duplicate_paragraph_chr_fraction": 0.0,
"response_entropy": 1.925080903607536,
"response_flesch_kincaid_grade": 10.533333333333335,
"response_flesch_reading_ease": 37.35500000000002,
"response_gunning_fog": 14.0,
"response_lix": 46.666666666666664,
"response_mean_word_length": 5.214285714285714,
"response_n_characters": 365,
"response_n_sentences": 6,
"response_n_stop_words": 26.0,
"response_n_tokens": 60,
"response_n_unique_tokens": 37,
"response_oov_ratio": 0.02857142857142857,
"response_passed_quality_check": "True",
"response_per_word_perplexity": 0.09793861849416963,
"response_perplexity": 6.855703294591874,
"response_pos_prop_ADJ": 0.05714285714285714,
"response_pos_prop_ADP": 0.1,
"response_pos_prop_ADV": 0.04285714285714286,
"response_pos_prop_AUX": 0.07142857142857142,
"response_pos_prop_CCONJ": 0.05714285714285714,
"response_pos_prop_DET": 0.07142857142857142,
"response_pos_prop_INTJ": 0.0,
"response_pos_prop_NOUN": 0.2571428571428571,
"response_pos_prop_NUM": 0.0,
"response_pos_prop_PART": 0.02857142857142857,
"response_pos_prop_PRON": 0.02857142857142857,
"response_pos_prop_PROPN": 0.0,
"response_pos_prop_PUNCT": 0.14285714285714285,
"response_pos_prop_SCONJ": 0.0,
"response_pos_prop_SYM": 0.0,
"response_pos_prop_VERB": 0.07142857142857142,
"response_pos_prop_X": 0.04285714285714286,
"response_prop_adjacent_dependency_relation_mean": 0.4988304093567251,
"response_prop_adjacent_dependency_relation_std": 0.017298478897952083,
"response_proportion_bullet_points": 0.0,
"response_proportion_ellipsis": 0.0,
"response_proportion_unique_tokens": 0.6166666666666667,
"response_rix": 3.6666666666666665,
"response_sentence_length_mean": 10.0,
"response_sentence_length_median": 13.0,
"response_sentence_length_std": 6.506407098647712,
"response_syllables_per_token_mean": 1.8833333333333333,
"response_syllables_per_token_median": 1.0,
"response_syllables_per_token_std": 1.2528855583101843,
"response_symbol_to_word_ratio_#": 0.0,
"response_token_length_mean": 5.916666666666667,
"response_token_length_median": 6.0,
"response_token_length_std": 3.742956347891626,
"response_top_ngram_chr_fraction_2": 0.13333333333333333,
"response_top_ngram_chr_fraction_3": 0.09285714285714286,
"response_top_ngram_chr_fraction_4": 0.14285714285714285
},
"responses": [],
"suggestions": [
{
"agent": null,
"question_name": "response",
"score": null,
"type": null,
"value": "1. Homogeneity: The segment should consist of customers who share similar characteristics and behaviors.\n2. Distinctiveness: The segment should be different from other segments in terms of their characteristics and behaviors.\n3. Stability: The segment should remain relatively stable over time and not change drastically. The characteristics and behaviors of customers within the segment should not change significantly."
}
]
}
```
While the same record in HuggingFace `datasets` looks as follows:
```json
{
"context": null,
"external_id": null,
"metadata": "{\"prompt_flesch_reading_ease\": 78.87285714285717, \"prompt_flesch_kincaid_grade\": 3.997142857142858, \"prompt_gunning_fog\": 8.514285714285714, \"prompt_automated_readability_index\": 1.24642857142857, \"prompt_coleman_liau_index\": 3.9114285714285693, \"prompt_lix\": 28.428571428571427, \"prompt_rix\": 1.5, \"prompt_entropy\": 0.4249943780917443, \"prompt_perplexity\": 1.5295818204705425, \"prompt_per_word_perplexity\": 0.0955988637794089, \"prompt_passed_quality_check\": \"True\", \"prompt_n_stop_words\": 7.0, \"prompt_alpha_ratio\": 0.8125, \"prompt_mean_word_length\": 3.6875, \"prompt_doc_length\": 16.0, \"prompt_symbol_to_word_ratio_#\": 0.0, \"prompt_proportion_ellipsis\": 0.0, \"prompt_proportion_bullet_points\": 0.0, \"prompt_duplicate_line_chr_fraction\": 0.0, \"prompt_duplicate_paragraph_chr_fraction\": 0.0, \"prompt_duplicate_ngram_chr_fraction_5\": 0.0, \"prompt_duplicate_ngram_chr_fraction_6\": 0.0, \"prompt_duplicate_ngram_chr_fraction_7\": 0.0, \"prompt_duplicate_ngram_chr_fraction_8\": 0.0, \"prompt_duplicate_ngram_chr_fraction_9\": 0.0, \"prompt_duplicate_ngram_chr_fraction_10\": 0.0, \"prompt_top_ngram_chr_fraction_2\": 0.0, \"prompt_top_ngram_chr_fraction_3\": 0.0, \"prompt_top_ngram_chr_fraction_4\": 0.0, \"prompt_oov_ratio\": 0.0, \"prompt_dependency_distance_mean\": 2.3181818181818183, \"prompt_dependency_distance_std\": 0.3181818181818181, \"prompt_prop_adjacent_dependency_relation_mean\": 0.28181818181818186, \"prompt_prop_adjacent_dependency_relation_std\": 0.08181818181818182, \"prompt_pos_prop_ADJ\": 0.0, \"prompt_pos_prop_ADP\": 0.0625, \"prompt_pos_prop_ADV\": 0.0625, \"prompt_pos_prop_AUX\": 0.0625, \"prompt_pos_prop_CCONJ\": 0.0, \"prompt_pos_prop_DET\": 0.0625, \"prompt_pos_prop_INTJ\": 0.0, \"prompt_pos_prop_NOUN\": 0.25, \"prompt_pos_prop_NUM\": 0.0625, \"prompt_pos_prop_PART\": 0.0625, \"prompt_pos_prop_PRON\": 0.0, \"prompt_pos_prop_PROPN\": 0.0, \"prompt_pos_prop_PUNCT\": 0.125, \"prompt_pos_prop_SCONJ\": 0.125, \"prompt_pos_prop_SYM\": 0.0, \"prompt_pos_prop_VERB\": 0.125, \"prompt_pos_prop_X\": 0.0, \"prompt_token_length_mean\": 4.071428571428571, \"prompt_token_length_median\": 3.5, \"prompt_token_length_std\": 2.5763841138387766, \"prompt_sentence_length_mean\": 7.0, \"prompt_sentence_length_median\": 7.0, \"prompt_sentence_length_std\": 3.0, \"prompt_syllables_per_token_mean\": 1.4285714285714286, \"prompt_syllables_per_token_median\": 1.0, \"prompt_syllables_per_token_std\": 0.7284313590846836, \"prompt_n_tokens\": 14, \"prompt_n_unique_tokens\": 14, \"prompt_proportion_unique_tokens\": 1.0, \"prompt_n_characters\": 59, \"prompt_n_sentences\": 2, \"response_flesch_reading_ease\": 37.35500000000002, \"response_flesch_kincaid_grade\": 10.533333333333335, \"response_gunning_fog\": 14.0, \"response_automated_readability_index\": 11.4375, \"response_coleman_liau_index\": 16.030000000000005, \"response_lix\": 46.666666666666664, \"response_rix\": 3.6666666666666665, \"response_entropy\": 1.925080903607536, \"response_perplexity\": 6.855703294591874, \"response_per_word_perplexity\": 0.09793861849416963, \"response_passed_quality_check\": \"True\", \"response_n_stop_words\": 26.0, \"response_alpha_ratio\": 0.7857142857142857, \"response_mean_word_length\": 5.214285714285714, \"response_doc_length\": 70.0, \"response_symbol_to_word_ratio_#\": 0.0, \"response_proportion_ellipsis\": 0.0, \"response_proportion_bullet_points\": 0.0, \"response_duplicate_line_chr_fraction\": 0.0, \"response_duplicate_paragraph_chr_fraction\": 0.0, \"response_duplicate_ngram_chr_fraction_5\": 0.14761904761904762, \"response_duplicate_ngram_chr_fraction_6\": 0.0, \"response_duplicate_ngram_chr_fraction_7\": 0.0, \"response_duplicate_ngram_chr_fraction_8\": 0.0, \"response_duplicate_ngram_chr_fraction_9\": 0.0, \"response_duplicate_ngram_chr_fraction_10\": 0.0, \"response_top_ngram_chr_fraction_2\": 0.13333333333333333, \"response_top_ngram_chr_fraction_3\": 0.09285714285714286, \"response_top_ngram_chr_fraction_4\": 0.14285714285714285, \"response_oov_ratio\": 0.02857142857142857, \"response_dependency_distance_mean\": 2.0984405458089666, \"response_dependency_distance_std\": 1.2368394170758057, \"response_prop_adjacent_dependency_relation_mean\": 0.4988304093567251, \"response_prop_adjacent_dependency_relation_std\": 0.017298478897952083, \"response_pos_prop_ADJ\": 0.05714285714285714, \"response_pos_prop_ADP\": 0.1, \"response_pos_prop_ADV\": 0.04285714285714286, \"response_pos_prop_AUX\": 0.07142857142857142, \"response_pos_prop_CCONJ\": 0.05714285714285714, \"response_pos_prop_DET\": 0.07142857142857142, \"response_pos_prop_INTJ\": 0.0, \"response_pos_prop_NOUN\": 0.2571428571428571, \"response_pos_prop_NUM\": 0.0, \"response_pos_prop_PART\": 0.02857142857142857, \"response_pos_prop_PRON\": 0.02857142857142857, \"response_pos_prop_PROPN\": 0.0, \"response_pos_prop_PUNCT\": 0.14285714285714285, \"response_pos_prop_SCONJ\": 0.0, \"response_pos_prop_SYM\": 0.0, \"response_pos_prop_VERB\": 0.07142857142857142, \"response_pos_prop_X\": 0.04285714285714286, \"response_token_length_mean\": 5.916666666666667, \"response_token_length_median\": 6.0, \"response_token_length_std\": 3.742956347891626, \"response_sentence_length_mean\": 10.0, \"response_sentence_length_median\": 13.0, \"response_sentence_length_std\": 6.506407098647712, \"response_syllables_per_token_mean\": 1.8833333333333333, \"response_syllables_per_token_median\": 1.0, \"response_syllables_per_token_std\": 1.2528855583101843, \"response_n_tokens\": 60, \"response_n_unique_tokens\": 37, \"response_proportion_unique_tokens\": 0.6166666666666667, \"response_n_characters\": 365, \"response_n_sentences\": 6}",
"prompt": "How to tell if a customer segment is well segmented? In 3 bullet points.",
"response": [],
"response-suggestion": "1. Homogeneity: The segment should consist of customers who share similar characteristics and behaviors.\n2. Distinctiveness: The segment should be different from other segments in terms of their characteristics and behaviors.\n3. Stability: The segment should remain relatively stable over time and not change drastically. The characteristics and behaviors of customers within the segment should not change significantly.",
"response-suggestion-metadata": {
"agent": null,
"score": null,
"type": null
}
}
```
### 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 supported. These are the ones that will be used to provide responses to the questions.
* **prompt** is of type `text`.
* (optional) **context** is of type `text`.
* **Questions:** These are the questions that will be asked to the annotators. They can be of different types, such as `RatingQuestion`, `TextQuestion`, `LabelQuestion`, `MultiLabelQuestion`, and `RankingQuestion`.
* **response** is of type `text`, and description "Write the response to the instruction.".
* **Suggestions:** As of Argilla 1.13.0, the suggestions have been included to provide the annotators with suggestions to ease or assist during the annotation process. Suggestions are linked to the existing questions, are always optional, and contain not just the suggestion itself, but also the metadata linked to it, if applicable.
* (optional) **response-suggestion** is of type `text`.
Additionally, we also have two more fields that are optional and are the following:
* **✨ NEW** **metadata:** This is an optional field that can be used to provide additional information about the dataset record. This can be useful to provide additional context to the annotators, or to provide additional information about the dataset record itself. For example, you can use this to provide a link to the original source of the dataset record, or to provide additional information about the dataset record itself, such as the author, the date, or the source. The metadata is always optional, and can be potentially linked to the `metadata_properties` defined in the dataset configuration file in `argilla.yaml`.
* **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
This is a supervised fine-tuning dataset that contains instructions. Please write the response to the instruction in the response field. Take the context into account when writing the response.
#### 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]
The dataset sharegpt-text-descriptives is created using Argilla, an open-source tool for data annotation and curation. It includes a configuration file in Argilla format and dataset records compatible with HuggingFaces `datasets` library. The dataset supports multiple NLP tasks based on its configuration, which includes fields like prompt and context, questions like response, and metadata for additional context. The dataset does not have a leaderboard and language information is not specified. An example instance shows detailed metadata about text characteristics and a suggested response.
