Viewing a Built-in Model in ModelArts Studio (MaaS)

ModelArts Studio provides various open-source models. You can check them on the Model Square page. The model details page shows all necessary information. You can choose suitable models for training and inference to incorporate into your enterprise systems.

Prerequisites

You have registered a Huawei account and enabled Huawei Cloud services.

Accessing the Model Square

Log in to the ModelArts Studio console and select the target region on the top navigation bar.
In the navigation pane on the left, choose Model Square.

In the Model Filtering area on the Model Square page, filter models by series, type, supported jobs, and context length, or search by model name.

For details about model series, see Models.

**Table 1** Model filtering
Filter Criteria	Description
Models	You can filter models by series, including all and DeepSeek.
Type	You can filter models by type, including all and text generation.
Supported Job Types	You can filter models by job type, including all, deployment, and tuning.
Context Length	You can filter models by context length, including all, fewer than 16K, and 16K.

Click Model Details below the target model. On the model details page, check the model's introduction, basic information, and version details.
On the model details page, click Tune, Compress, or Deploy on the right to train or use the model.
The model does not support that task if you see a grayed-out button.

Models

Table 2 lists the models supported by ModelArts Studio. For details about the models, go to the model details page.

**Table 2** Models in the Model Square
Model		Type	Use Case	Supported Language	Supported Regions	Model Introduction
DeepSeek	DeepSeek-R1	Text generation	Q&A and text generation inference	Chinese and English	CN-Hong Kong	DeepSeek-R1 model. It uses advanced technology for long-context understanding and fast inference. The model supports multi-modal interactions and API integrations. It enhances applications like intelligent customer service and data analytics, offering top cost-effectiveness for intelligent upgrades of enterprises.
	DeepSeek-V3	Text generation	Q&A and translation	Chinese and English	CN-Hong Kong	DeepSeek-V3 is a strong Mixture of Experts (MoE) language model. It uses a new load balancing method without extra loss and aims for better performance with multi-token predictions.
	DeepSeek-R1-Distill-Qwen-14B	Text generation	Q&A and text generation inference	Chinese and English	CN-Hong Kong	Qwen-14B is distilled from DeepSeek-R1 outputs and matches the capabilities of OpenAI o1-mini. DeepSeek-R1 performs similarly to OpenAI-o1 in math, coding, and inference tasks.
	DeepSeek-R1-Distill-Qwen-32B	Text generation	Q&A and text generation inference	Chinese and English	CN-Hong Kong	Qwen-32B is distilled from DeepSeek-R1 outputs and matches the capabilities of OpenAI o1-mini. DeepSeek-R1 performs similarly to OpenAI-o1 in math, coding, and inference tasks.