Deploy

This guide will show you how to customize an LLM for your application. We’ll cover how to get started using one of our API clients and how to make your first API request. We’ll also look at where to go next to find all the information you need to take full advantage of our powerful REST API.

​

Model Formats

Model conversion are available once you’ve fine-tuned a model. Select your model from the Models tab and you’ll be presented with your model’s dashboard. Within the right panel of the dashboard, click the “Options” dropdown button and descend into the “Downloads” button. Another dropdown menu will be presented with conversion options. Click to download a converted model in your desired format.

Model tasks and architectures support varies in conversion options. Generally, we support:

Image-based model tasks like classifiers, detectors, and segmentors support the following formats:

• Micro
• CoreML
• TFlite
• ONNX
• Blob

Text-based model tasks like text generators and text embedding models support the following formats:

• Adapters
• gguf
• llamafile

Each format will also include code examples for running inference under the “Code Samples” dropdown button within the “Options” dropdown button.

​

Deploy

You can also deploy a GPU-optimized local server automatically using the Remyx CLI! You can find the instructions for your text generation model by clicking the “Options” dropdown button, under the “Deploy” option. Clicking the “GPU” option will present a popup walking through the process.

​

What’s next?

Amazing! You’ve customized a model for your use case! Read more about:

• Building AI applications in the ML in a Minute series on YouTube