Introducing AI Playground — LLM Battleground to Check Highly effective AI Fashions

This weblog publish focuses on new options and enhancements. For a complete record, together with bug fixes, please see the launch notes.

AI Playground

We’re excited to introduce the brand new AI Playground, your interactive llm battleground to discover, check, and construct with highly effective AI fashions. Whether or not you are a developer evaluating mannequin efficiency, a product supervisor prototyping options, or simply interested by what a mannequin can do, the Playground provides you speedy hands-on entry with none setup.

The Playground brings collectively a curated assortment of trending fashions throughout imaginative and prescient, language, and multimodal duties. A few of the fashions you possibly can check embody DeepSeek-R1-Distill-Qwen-7B, Llama 3.2, Qwen 2.5-VL, Gemma 3.0, and MiniCPM. You may enter your personal information, get real-time outputs, evaluate outcomes, and perceive how fashions behave — all from one clear, intuitive interface. We now assist streaming, so you possibly can work together with language fashions as they generate outputs token by token, similar to in a chat.

To make the expertise much more developer-friendly, each mannequin within the Playground features a ready-to-use API code snippet. With a single click on, you possibly can copy the code and begin integrating that mannequin instantly into your personal AI apps. No have to dig by means of documentation or work out the proper configuration. It’s accessible immediately.

You may as well deploy neighborhood fashions instantly from the Playground to your personal devoted compute. This makes it simple to maneuver from experimentation to manufacturing with out leaving the interface.

We constructed the AI Playground to make it simpler to go from testing a mannequin to deploying it. You not want to change instruments, write additional code, or arrange infrastructure simply to see how a mannequin works. This simplifies the method from exploration to deployment.

Labeling Duties

• We’ve upgraded the Labeling Duties UI to supply a smoother and extra constant expertise. This replace brings the duty labeling interface according to our unified Enter Viewer part, guaranteeing consistency throughout the platform and making it simpler for customers to navigate and label with confidence.

Platform Updates

Redesigned Homepage

• We launched a redesigned homepage that can assist you get began with the Clarifai platform extra rapidly

• Now you can simply uncover trending AI fashions, check them within the playground, arrange your computing infrastructure, browse your apps, and extra — multi functional centralized place.

• You may as well customise your homepage format utilizing the “Configure House” button within the upper-right nook.
  

Made platform enhancements

• Launched a brand new Infrastructure Supervisor position, permitting customers to create, modify, and delete clusters and nodepools inside a company.
• Eliminated the automated app onboarding move for brand new customers upon signup. Apps are not required for sure actions, comparable to making deployments with Compute Orchestration.
• We now robotically fetch a consumer’s full title after signing up with SSO through Google or GitHub, eliminating the necessity to manually enter it throughout the signup move.
• We improved the “Member Since” column within the group members record desk. It now shows when a member joined the group, quite than after they assumed their present position.
• We restricted entry to the group members record to admins solely.

We’ve made loads of updates to the Management Heart to make it extra intuitive and simpler to navigate.

• Refined desk layouts for improved readability and readability.
• Launched a brand new multi-column tooltip for charts, enhancing information visibility and readability.
• Mounted a coloration inconsistency the place the tooltip card displayed an incorrect coloration when hovering over chart components. The tooltip now precisely displays the corresponding chart section coloration.
• Mounted a difficulty the place the utilization dashboard did not appropriately report prices for deleted fashions.

Further adjustments – Python SDK

We’ve made a number of enhancements to the Python SDK to enhance usability, and developer expertise:

• Eliminated HF loader config.json validation for all Clarifai mannequin kind IDs.
• Added regex patterns to filter checkpoint information for obtain.
• Applied validation for CLI configuration.
• Mounted Docker picture title and launched the skip_dockerfile possibility within the test-locally subcommand of the Mannequin CLI.

Study extra right here in regards to the newest updates.

Prepared to begin constructing?