Windows AI Studio PreviewOverviewWindows AI Studio simplifies generative AI app development by bringing together cutting-edge AI development tools and models from Azure AI Studio Catalog and other catalogs like Hugging Face. You will be able browse the AI models catalog powered by Azure ML and Hugging Face for public models that you can download locally, fine-tune, test and use them in your Windows application. As all of the computation happens locally, please make sure your device can handle the load. Quick StartIn this section you will learn how to quickly start with Windows AI Studio. PrerequisitesWindows AI Studio will run only on NVIDIA GPUs for the preview, so please make sure to check your device spec. WSL Ubuntu distro 18.4 or greater should be installed and is set to default prior to using Windows AI Studio. learn more how to install Windows subsystem for Linux and changing default distribution Install Windows AI Studio PreviewWindows AI Studio is shipped as a Visual Studio Code Extension, so you need to install VS Code first, and download Windows AI Studio from the VS Marketplace. Available ActionsUpon launching Windows AI Studio, you can select from the following options:
Model Fine-tuningTo initiate the local fine-tuning session using QLoRA, select a model you want to fine-tune from our catalog powered by AzureML.
Start by selecting a project name and location. Next, select a model from the model catalog. You will be prompted to download the project template. You can then click Configure Project to adjust various settings. We use Olive to run QLoRA fine-tuning on a PyTorch model from our catalog. All of the settings are preset with the default values to optimize to run the fine-tuning process locally with optimized use of memory. After all the parameters are set, click Generate Project. This will:
When the model is downloaded, you can launch the project from Windows AI Studio. Windows Optimized ModelsThis is the collection of publicly available AI models already optimized for Windows. The models are stored in the different locations including Hugging Face, GitHub and others, but you can browse the models and find all of them in one place ready for downloading and using in your Windows application. |