# **Model Plaza**

The "Model Plaza" of the ModelVerse large-scale model service platform offers multiple well-known open-source large models pre-installed to meet the needs of different business scenarios. You can browse, search, and experience models in the "Model Plaza," supporting online fine-tuning, evaluation, and one-click deployment to quickly apply large models to your business.

## **Accessing Model Plaza**

Click on the product "Model Service Platform UModelVerse" — and the menu "Model Plaza" — to view multiple large models and their related operations.

## **Home Page Operations of the Plaza**

Through the tag area of the model plaza, you can search for the list of models you need, supporting multi-selection of tags and clearing filter conditions.
- Filter: You can filter by language and context length.
- Sorting: Above the model list, comprehensive sorting is supported, including sorting by model update time and model name.
- Search: You can search by model name in the search box.
<!-- image-todo -->

## **Model Operations**

Click the model card to enter the model detail page, including basic information such as the model name, model type, and model description.
<!-- image-todo -->

### **Fine-Tuning**

Supports further fine-tuning of some models in the model plaza. Click "Fine-Tune" to create a fine-tuning task. For specific support ranges, please refer to the relevant content of **Model Fine-Tuning**.

### **Evaluation**

Supports evaluating the effect of some models in the model plaza. Click "Evaluate" to initiate an evaluation task. For specific support ranges, please refer to the relevant content of **Model Evaluation**.

### **Deployment**

Supports online deployment of some models in the model plaza. Click "Deploy" to perform model deployment, and refer to the **Service Deployment** related content for detailed operations.

## **Overview of Supported Models and Operations in Model Plaza**

| Model Category    | Model                                        | Operations                             |
|-------------------|----------------------------------------------|----------------------------------------|
| **DeepSeek Series** | DeepSeek R1                               | **Experience, API Call (Billing starts 2025.3.31)** |
|                   | DeepSeek V3                               | **Experience, API Call (Billing starts 2025.3.31)** |
| **Qwen Series**    | Qwen/Qwen2.5-14B-Instruct                 | Fine-Tuning, Evaluation, Deployment    |
|                   | Qwen/Qwen2.5-0.5B-Instruct                | Fine-Tuning, Evaluation, Deployment    |
|                   | Qwen/Qwen2.5-1.5B-Instruct                | Fine-Tuning, Evaluation, Deployment    |
|                   | Qwen/Qwen2.5-7B-Instruct                  | Fine-Tuning, Evaluation, Deployment    |
|                   | Qwen/Qwen2-7B-Instruct                   | Fine-Tuning, Evaluation, Deployment    |
|                   | Qwen/Qwen1.5-14B-Chat                    | Fine-Tuning, Evaluation, Deployment    |
|                   | Qwen/Qwen1.5-7B-Chat                     | Fine-Tuning, Evaluation, Deployment    |
| **Meta-Llama Series** | meta-llama/Meta-Llama-3.1-8B-Instruct   | Fine-Tuning, Evaluation, Deployment  |
|                   | meta-llama/Llama-2-13b-chat-hf            | Fine-Tuning, Evaluation, Deployment  |
|                   | meta-llama/Llama-2-7b-chat-hf             | Fine-Tuning, Evaluation, Deployment  |