From now on, more than 100 million developers on GitHub can directly access the world's top large models to build AI applications

The new feature "GitHub Models" launched by GitHub is expected to accelerate the arrival of the era of AI engineers.

What? The familiar code hosting platform GitHub has evolved again! The platform has also begun to provide Playgroud for large AI models.

All the popular large models in the industry that you can name, including Microsoft's Phi-3, OpenAI's GPT-4o, Meta's Llama 3.1, Cohere's Command R+, and Mistral AI's Mistral Large, can be used in an interactive Try it out in the sandbox.

In the coming months, Github will also add more language, visual and other types of models.

In other words, all the models in this picture can be purchased for free! It is equivalent to a new way to test various large models for free!

Not only that, developers can also easily import suitable models into their own AI projects. Github has created a fast channel that can directly place models in the Codespaces and VS Code development environments, lowering the threshold for deploying AI models.

This is the “GitHub Models” feature launched by GitHub today!

For developers, as long as they have the right tools and training, everyone can become an AI engineer. Developers select models, code in GitHub Codespaces, and then deploy them to production through Azure, providing a "one-stop" service.

Specifically, you can call the GitHub Models command in GitHub CLI and use it in GitHub Actions through a series of JSON files. You can also use GitHub Models to build GitHub Copilot extensions, covering the entire cycle of application development.

When the project enters the online stage, Github also provides seamless integration with Azure AI. Github's authentication can be subscribed through Azure, and the threshold for deploying AI applications to the production environment is thus lowered.

Now, you can deploy AI applications in more than 25 Azure regions around the world through Github and get Azure’s enterprise-grade security protection.

Consistent with GitHub and Microsoft’s ongoing commitment to privacy and security, any tips or output from GitHub models are not shared with model providers or used to train or improve the model.

Of course, trying out "GitHub Models" is not completely unrestricted. Individual users are limited to 150 access times per day and no more than 15 times per minute. Each request can process up to 8,000 tokens and output up to 4,000 tokens.

In this regard, GitHub CEO Thomas Dohmke said that the launch of this feature marks another transformation of GitHub, from creating AI through open source collaboration to creating software with the power of AI, and now using GitHub Models to promote the development of AI engineers. rise.

And based on OSS repositories, Copilot Extensions and GitHub Models functions, GitHub hopes to introduce as many partners as possible to its platform.

Some developers showed a case of running the model directly in the GitHub code space. There is no need to install anything and it can be started in a few seconds.

                                           ^{After Hugging Face becomes "Hugging Face", how will Hugging Face respond?}

The above is the detailed content of From now on, more than 100 million developers on GitHub can directly access the world's top large models to build AI applications. For more information, please follow other related articles on the PHP Chinese website!