ModelArts Studio (MaaS) Usage
MaaS offers a complete toolchain for creating foundation models using compute resources. It comes with ready-to-use popular open-source foundation models. It is designed for users who need to develop production-ready models using a MaaS platform.
Context
AI models now play a vital role in driving enterprise digital transformation due to their advanced abilities in understanding language, generating content, and making decisions. Many businesses aim to improve operations using foundation models for tasks like customer support, data analytics, and automatic reporting. However, they encounter three main hurdles when they train or fine-tune foundation models: expensive compute, complicated technical demands, and integrating these systems into existing workflows. Since most companies lack skilled AI teams, building and refining models from scratch proves challenging. This often leads to slow deployments and project failures.
To tackle these challenges, MaaS offers a one-stop solution:
- Toolchain: Offers a visual training platform that simplifies model customization for businesses, requiring minimal AI expertise.
- Resource sharing: Cloud compute enables resource sharing by allowing companies to share compute and reuse pretrained models, cutting down on duplicate expenses and lowering overall compute costs.
- Scenario adaptation: Preset model templates tailored for specific industries help speed up the deployment of enterprise AI applications.
Use Cases
This section describes MaaS use cases:
- Integration of popular open-source models
MaaS integrates leading open-source models, including Qwen and DeepSeek. All models are fully adapted and optimized, resulting in improved accuracy and performance. You no longer need to build models from scratch; instead, you can simply choose suitable pre-trained models for direct application, reducing the workloads of model integration.
- Accessible resources, pay-per-use billing, scalability, fast fault recovery, and resumable training
Businesses using foundation models must evaluate both performance and real-world accuracy and costs.
MaaS delivers flexible model development tools to enable effective integration of these models into customer operations.
It allows you to scale resources on demand, with pay-per-use billing. This minimizes wasted resources and makes AI more accessible by lowering initial investment.
The architecture prioritizes high availability by duplicating data centers, so you can rest assured that your work is backed up at all times. In case of failure, the system automatically shifts to a standby setup, maintaining uninterrupted progress with no wasted time or resources.
- Application development, helping you build applications quickly
In enterprises, complex project-level tasks often require understanding the task, breaking it down into multiple decision-making questions, and then calling various subsystems to execute. MaaS uses advanced open-source models to accurately grasp business goals, break down tasks, and create multiple solutions. It helps businesses quickly and intelligently build and deploy LLM-powered applications.
Supported Regions
MaaS is available only in the CN-Hong Kong region.
Usage Process
The table below shows the core process of using MaaS.
Module |
Operation |
Description |
Helpful Links |
---|---|---|---|
Authorization |
Configuring access authorization |
All users (including individual users) can use MaaS only after agency authorization on ModelArts. Otherwise, unexpected errors may occur. |
|
Real-time inference service |
Checking built-in models in the Model Square |
ModelArts Studio provides various open-source models. You can check them on the Model Square. The model details page shows all necessary information. You can choose suitable models for inference to incorporate into your enterprise systems. |
|
Subscribing to a built-in commercial service |
MaaS offers commercial services that give businesses high-performance, reliable inference APIs. Billing is based on token usage. Commercial services fit situations needing high stability, frequent calls, and expert support. |
Subscribing to a Built-in Commercial Service in ModelArts Studio (MaaS) |
|
Deploying a model |
You can deploy built-in models from Model Square using compute resources so that you can call the models in other service environments. |
||
API calls |
Calling a model service |
After a model is deployed, you can call the model service in other service environments for prediction. |
|
Model management |
Creating a model |
ModelArts Studio provides open-source foundation models. You can use these foundation models and custom model weight files to create your own models. After a model is created, you can use it for inference. |
|
Management and statistics |
Viewing service call data and monitoring metrics |
MaaS offers call statistics. You can view call data and monitoring metrics for your services and built-in commercial services over a set time. This includes total calls, failed calls, total tokens, input tokens, output tokens, and average response latency. Data trends are shown hourly, which helps you understand usage and performance changes. This helps you evaluate models, find issues, fix problems, and improve performance. |
Viewing Call Data and Monitoring Metrics of ModelArts Studio (MaaS) |
Feedback
Was this page helpful?
Provide feedbackThank you very much for your feedback. We will continue working to improve the documentation.See the reply and handling status in My Cloud VOC.
For any further questions, feel free to contact us through the chatbot.
Chatbot