AI devs can now make use of GitHub Models, new alternative to Hugging Face

GitHub has launched GitHub Models, a new feature that lets developers test and compare AI models right within GitHub, Codespaces, and Visual Studio Code. This makes it easier for developers to work with AI without switching tools—almost a direct competitor to the popular Hugging Face platform.

The Microsoft-owned platform said that GitHub Models supports popular AI models like Meta’s recently launched Llama 3.1 and OpenAI’s GPT-4o. Unlike Microsoft Azure, which requires a complex setup, GitHub Models are available immediately, and it’s currently currently in public beta for you to try on.

“With GitHub Models, more than 100 million developers can access and experiment with new AI models where they already manage their source code, issues, pull requests, workflows, and repositories – directly on GitHub,” GitHub’s CEO Thomas Dohmke says.

Hugging Face has been one of the most popular platforms for AI developers for quite some time, but it seems like it’s facing direct competition from GitHub.

While Hugging Face does host a wide range of AI models, that’s for sure, GitHub’s deep integration with dev tools like Codespaces and Visual Studio Code makes things easier for developers to test and use these AI models directly within the coding environment. It’s something that the former does not have compared to GitHub Models.

There are plenty of new AI models being launched in recent weeks or months. OpenAI’s new GPT-4o and its “mini” variant have been making the buzz, while Meta’s Llama 3.1 is the most impressive one for an open-source model and it’s also available on Amazon Bedrock.

If you’re interested, you can try GitHub Models’ public beta here.