Tech
Introducing GitHub Models, a new feature that allows you to test AI models such as GPT-4o and Llama 3.1 at no cost.
Introducing GitHub Models new feature
GitHub Models is a newly introduced feature that allows users to experiment with a variety of popular large language models from leading organizations like Meta, OpenAI, Mistral, and others.
GitHub, the widely-used cloud-based platform with over 100 million developers globally, now offers a new feature that enables you to explore different AI models such as GPT-4o, Llama 3.1, Mistral Large 2, and more.
This feature, named “GitHub Models,” is designed to enhance accessibility for developers by seamlessly integrating with existing tools. It allows developers to test various prompts and model parameters within their current environment at no cost.
In a blog post, GitHub noted, “If you like what you’re seeing on the playground, we’ve created a glide path to bring the models to your developer environment in Codespaces and VS Code,” which aims to accelerate the transition from prototype to production for AI applications.
GitHub’s new interactive playground is not only beneficial for developers but also accessible to students, startups, and hobbyists, allowing them to explore the latest models from Meta, OpenAI, Azure, and others with just a single click.
The new playground feature shares similarities with offerings from OpenAI, which also allows testing of different parameters and code generation. GitHub assures that it will not share outputs or prompts with providers nor use them to train or enhance existing models.
With the launch of GitHub Models, GitHub enters direct competition with HuggingFace, a platform known for hosting popular AI models but lacking the integration and advanced tools provided by GitHub. The feature is currently in public beta and available to a select group of users, with developers needing to sign up for a waitlist.
Post a comment