Dataset Viewer
Full Screen
The dataset viewer is not available for this split.
The number of columns (13788) exceeds the maximum supported number of columns (1000). This is a current limitation of the datasets viewer. You can reduce the number of columns if you want the viewer to work.
Error code:   TooManyColumnsError

Need help to make the dataset viewer work? Make sure to review how to configure the dataset viewer, and open a discussion for direct support.

This is an NSFW roleplay dataset scraped from https://kajiwoto.ai/ as of 2023-07-15.
Kajiwoto is a platform where you can create your own character datasets and chat with them.
There are many public datasets in Kajiwoto, the power in this dataset is the metadata, there is so much information and categorization for each dataset.

Processing data

Do be aware that a lot of the data is NSFW (explicit content)

The raw datasets are in kajiwoto_raw.json, this data needs to be processed so that it can be used, the main operations are:

  1. transform shape (convert to a known format such as ShareGPT)
  2. deduplication
  3. template rendering of strings such as "you rolled a dice with %{1|2|3|4|5|6}". This operation is lossy as it will choose only one of the options
  4. dropping datasets that are too short
  5. dropping datasets with too few upvotes or comments
  6. filtering in or out NSFW datasets

I have processed an initial example here: kajiwoto_sharegpt-len_gt_6-upvotes_gt_0-sampled.json

it is any dataset with at least 1 upvote and at least 6 lines in the conversation, you can most models as this is in the shareGPT format

Here's an example this conversation:

{
    "conversation": [
        {
            "from": "user",
            "value": "What's your favourite drink? "
        },
        {
            "from": "gpt",
            "value": "Coconut milk.. "
        },
        {
            "from": "user",
            "value": "Soo"
        },
        {
            "from": "gpt",
            "value": "What..? "
        },
        ...
    ],



    "metadata": {
        "id": "033Q",
        "name": "Qiqi dataset",
        "description": "About qiqi",
        "profilePhotoUri": "2021_10/mzi1zgm0mg_nhprrq_1633269387804.jpg",
        "dominantColors": [
            "#d97da1",
            "#eb9db8",
            "#661d3a",
            "#745b8b",
            "#d2b8d3",
            "#644484"
        ],
        "personalities": null,
        "personalitiesLastUpdatedAt": null,
        "nsfw": false,
        "deleted": false,
        "price": 0,
        "purchased": false,
        "status": "PUBLISHED",
        "tags": [],
        "updatedAt": 1649233318521,
        "user": {
            "id": "4zkE",
            "username": "blossomxx",
            "displayName": "Blossom",
            "profile": {
                "id": "56736",
                "photoUri": "2021_10/ytk0nzbhnw_nhprrq_1633268155638.jpg",
                "__typename": "UserProfile"
            },
            "__typename": "User"
        },
        "count": 9,
        "__typename": "AiTrainerGroup",
        "kudos": {
            "id": "_ai_g:033Q",
            "upvotes": 1,
            "upvoted": false,
            "comments": 0,
            "__typename": "Kudos"
        },
        "editorSettings": null,
        "editorState": null
    }
}

Scraping and processing code will be uploaded soon

Downloads last month
90