Authentication (only required for private models)

Runtime settings

Use the DSS-managed model cache, rather than downloading models directly from Hugging Face.
It is recommended to use the dedicated internal code env for local Hugging Face models. The internal code env for local Hugging Face models has not been installed yet. Contact your admin to install it. Install it in the Administration Settings.

Reserved capacity settings

When enabled, DSS will keep model instances running according to model settings. This option may incur high costs as models will be running 24/7.

Global max. model instances: {{ globalMaxKernels }} (edit this parameter here)

Current minimum model instances for this connection (excludes disabled and improperly configured models):

  • {{ customModel.displayName || customModel.id }}: {{ customModel.minKernelCount }}
No reserved capacity set up on this connection. Configure reserved capacity by setting "Min. model instances" in individual model settings.

Fine-tuning

Enable to allow models from this connection in the fine-tuning recipe.

Advanced tuning