> For the complete documentation index, see [llms.txt](https://nx.docs.scailable.net/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://nx.docs.scailable.net/ai-manager-v6.1.3/ai-models-support/importing-models/from-nota-ai.md).

# From Nota AI

## About Nota AI

Nota AI provides a software optimization platform, focusing on reducing the time and resources required to develop an artificial intelligence (AI) model and **optimizing** it for the target device.

Nota AI developed [NetsPresso](https://www.nota.ai/netspresso), which is a hardware-aware AI model optimization platform. The platform focuses on optimizing AI models to run efficiently on various hardware devices. They provide a set of [free optimized models](https://launchx.netspresso.ai/models) for various tasks.

## Deploying models

To upload NetsPresso models to AI Platform, export your AI model from [LaunchX](https://launchx.netspresso.ai/main) to **TFLite**. Then upload the `.tflite` file using the **Add a model** wizard in the [platform](/ai-manager-v6.1.3/ai-cloud-ui/upload-your-model.md). The wizard detects the file format automatically. Complete all five steps: upload the file, set an owner, optionally assign a catalogue, choose hardware targets, and add a name and documentation.

<figure><img src="/files/5oTcrdaC90bLhoW0PRYr" alt="Add a model wizard showing the Upload a Model File step with a drag-and-drop area"><figcaption><p>Drag and drop your TFLite file into the upload area to start the wizard.</p></figcaption></figure>

After the model is converted on the AI Platform, set the correct mean and standard deviation values that were used during training. Go to the model page, click the **Edit** button, and update the normalization values and any other model parameters such as input width and height. Click **Save** when done.