How to Use Model Catalog?

Each model card includes:

  • Model Name (e.g., Qwen/Qwen3-14B, meta-llama/Llama-3-70B)

  • Provider (e.g., Qwen, Meta LLaMA, Google Gemma, DeepSeek, IBM Granite, Mistral)

  • Version or Size (e.g., 7B, 14B, 70B)

Each model card provides multiple options via the three-dot menu (⋮):

  • Playground

    Test the model directly in the Playground interface. You can interact with it before deployment.

  • Create API Endpoint

    Generate an API endpoint for the model so it can be integrated into your applications or services.

  • Fine-tune

    Customize the model using your own dataset to improve performance for your specific use case.

file

Browsing and Searching Models

  • Use the search bar at the top to quickly find a model by name.

  • Use the filter tabs (e.g., DeepSeek, GPT, Qwen, etc.) to view models from a specific family.

  • At the bottom right, adjust the “Models per page” setting to display 8, 16,32, 64, or more models per page.

  • Navigate between pages using the pagination controls.

PreviousHow to Use Models from Other Sources like Hugging Face?NextModel Fine-tuning

Last updated