# Manage Model

Through the History menu in GNB, you can manage your model.

## Train Model 

If you press the 'Train Model' button at top of the Dashboard page, the model version is updated through training data and a new one is created.

<figure><img src="/files/sba1B5EbWNmu7655Jf2R" alt=""><figcaption><p>GNB > Dashboard > Train Model</p></figcaption></figure>

## Create Model&#x20;

Once a model training is done, you can check the created model along with the following information **at the top of the model list** on History page.

<figure><img src="/files/JkygmROUNPo5sjKodomv" alt=""><figcaption><p>GNB > History > Model History > Created Model after finishing training</p></figcaption></figure>

* Model name
* Number of training/test data samples
* Performance Metrics (Precision, Recall, Accuracy, F1 score)
* Created time

##

## Deploy Model&#x20;

If you confirmed that the model has the desired performance, it can be deployed by clicking the 'Deploy' button in the Actions column.&#x20;

<figure><img src="/files/chGse9b53VK8mkUOfdbe" alt=""><figcaption><p>GNB > History > Model History > Deploy button</p></figcaption></figure>

{% hint style="info" %}
When the deployment is complete, the button is displayed as Deployed as its status.
{% endhint %}

## Edit/Delete Model&#x20;

You can edit or delete the model name through the Edit/Delete menu in the right column whenever you want.&#x20;

<figure><img src="/files/XSBGN7lncW0NqRhT49H9" alt=""><figcaption><p>GNB > History > Model History > Edit/Delete Model</p></figcaption></figure>

{% hint style="warning" %}
Please be careful as once deleted models cannot be restored.
{% endhint %}

## Check Performance

You can also check the model's performance from History page.&#x20;

{% content-ref url="/pages/k7ESygWBBYYWBiC2gBk2" %}
[Performance Metrics](/nlu-api-dashboard/model-management/performance-metrics.md)
{% endcontent-ref %}

{% hint style="info" %}
You cannot start training another model on Dashboard before you finish applying the recently created model. \
If you want to train a new model, you can do so by **deleting 'the recently created but not deployed' model**.
{% endhint %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.allganize.ai/nlu-api-dashboard/model-management/manage-model.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.