Model Catalog
Model Catalog provides users with pre-set model services, featuring mainstream large models from around the world for development, training, tuning, and inference deployment.
Introduction
Users can select corresponding models according to business needs for development, training, tuning, inference deployment, and other services. Model Catalog mainly includes the following models:
- Llama2, Llama3, Llama3-Language-8B, etc.
- Bert
- ChatGlm2, ChatGlm3
- Deepseekv2, Deepseekv3
- Baichuan2
Prerequisites
- The management console account and password have been obtained.
Procedure
- Log in to the management console.
- In the top navigation bar, click Products and Services > AI Computing Platform > AI Computing Platform to go to its overview page.
- In the left navigation bar, select Model Catalog to enter the Model Catalog page. Users can filter the model list according to application scenarios or framework type labels.
Note:
- Application scenario model labels currently include text, images, natural language processing, or computer vision.
- Framework type model tags currently include TensorFlow or PyTorch.
- All tag filtering logic is OR relational.
-
Enter the Model Catalog page and search for the corresponding model by entering key fields in the search box at the top.
-
On the Model Catalog page, hover the mouse over a specific model and click Online Inference to create an online inference service based on the current model. You can create an online inference service directly from here.
-
On the Model Catalog page, click a specific model to enter its details page, which introduces the model effect, model deployment, Web application, computing resource requirements, and model available areas and resources of the current model.
Note:
- You can also create an online inference service based on the current model directly on the model details page.