Model Management is designed to streamline the process of selecting, using, and deploying LLM models. With a diverse range of over 80 foundation models at your disposal, you can find the perfect fit for your specific use case without the need for extensive training.

Explore and Deploying Model

In the LLM menu, select 'Models'.

After that, you will be redirected to the ‘Models’ page. Here you can see a lot of models that you can use.

Deploy the Model

To deploy the model, you can just simply choose the model and click “Deploy model” button. And after that a dialog will show, in this dialog you need to input the API KEY for the model you choose.

If you successfully “Add the credentials” for the model that you choose, the model card will be changed into deployed.

My models

The "My models" page enhances your experience, giving you control and flexibility over your chosen models.

You can connect and synchronize your models with external platforms such as OpenAI and AWS Sagemaker Jumpstart directly from the "My Models" page.

You can also edit to change the API KEY, or disconnect the providers from your page.

Notes: Currently, our system only supports OpenAI for editing the API key.

Last updated