Master LLMs with our FREE course in collaboration with Activeloop & Intel Disruptor Initiative. Join now!

Publication

Build a Personal ML Model Registry with Replicate in 5 mins
Latest   Machine Learning

Build a Personal ML Model Registry with Replicate in 5 mins

Last Updated on April 22, 2024 by Editorial Team

Author(s): Tim Cvetko

Originally published on Towards AI.

Developer’s Guide to Hosting any ML Model and Charging for It

Coders have GitHub. Designers have Behance. Damn it, why can’t I have a portfolio full of ML models?! 🙂

The idea is simple: I want to be able to:

Showcase my work in a single “ML portfolio”Allow other ML engineering teams to use my models for inference.+ I want to get paid per API callWalkthroughUse Replicate SDK to create and deploy ML Models automaticallyBuild the Predictor around any model for InferenceUse Stripe Connect to get Paid per API bilingBuild a Tailwind UI ML frontend/portfolio

Join the discussion on this topic here: https://forms.gle/AJFCDmpknzbh3UNw6

A trained model in a directory on your computer. Your model’s saved weights, alongside any code that is needed to run it. If you don’t already have your own trained model, you can use one from replicate/cog-examples.Docker. You’ll be using the Cog command-line tool to build and push your model. Cog uses Docker to create a container for your model. You’ll need to install and start Docker before you can run Cog. You can confirm Docker is running by typing docker info in your terminal.If your model needs a GPU, a Linux machine with an NVIDIA GPU attached and the NVIDIA Container Toolkit installed. If you don’t already have access to a… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI

Feedback ↓