> For the complete documentation index, see [llms.txt](https://docs.datasaur.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.datasaur.ai/advanced/extensions/datasaur-dinamic.md).

# Datasaur Dinamic

## Overview

**Datasaur Dinamic** lets you train and deploy models directly from your labeled data. The trained model can be used in your applications or as a provider in the **ML-assisted labeling** extension for future projects. Because the model is trained on your dataset, it can generate more accurate predictions for similar labeling tasks.

<figure><img src="/files/lbgBlvcm9agY3jdpXl3q" alt=""><figcaption><p><strong>Datasaur Dinamic</strong> extension with AWS SageMaker</p></figcaption></figure>

## Quick guide

This example uses **Datasaur Dinamic** to train an NER model with a text-based dataset.

1. Label your dataset manually or using assisted labeling features such as **ML-assisted labeling** or **Predictive labeling**.

   <figure><img src="/files/sULJ0bE8R9pnbeqBNQLr" alt=""><figcaption></figcaption></figure>
2. Click the gear icon in the extension panel on the right to open the **Manage extensions** dialog, then enable the **Datasaur Dinamic** extension.

   <figure><img src="/files/C3I16RaCCPmGZHyCGRrO" alt=""><figcaption></figcaption></figure>
3. Select a service provider in the extension. In this example, use **Hugging Face AutoTrain** for a span labeling task.
   1. Enter your Hugging Face username from [Account settings](https://huggingface.co/settings/account).
   2. Provide a [Hugging Face token](https://huggingface.co/settings/tokens) or create a new access token.

      <figure><img src="/files/6f9ZEPvpQNf8eovqJ94S" alt=""><figcaption></figcaption></figure>

{% hint style="info" %}
For more information and supported providers, see [Datasaur Dinamic](/build-model/datasaur-dinamic.md).
{% endhint %}