Adding a Model to Ollama

Open https://ollama.com/search to check the models supported by ollama, and select a model you'd like to pull. For example, I want to pull the deepseek-r1:70b model.

Pulling a Model via Open-WebUI

• Install the Open WebUI application; click to jump

• Click the model name in the upper-left corner of Open-WebUI. This will open a dropdown menu allowing you to switch models.

  

• When the dropdown list does not contain the model you need, manually enter a deepseek-r1:70b in the search box. The interface will then prompt: "Pulling deepseek-r1:70b from Ollama.com"

  

• Click "Pulling deepseek-r1:70b from Ollama.com", which will initiate the background model download. The interface will also display the progress.

  

Pulling a Model via Ollama Command Line

• First, you need to log into the AI Pod system via SSH or directly through the display screen.
• Execute docker exec -ti cloudlazycataipodwebollama-ollama-1 bash to enter the container ollama
• Execute ollama pull deepseek-r1:70b accordingly

Pulling models with webollama

1. Install the webollama application, click to jump

2. After opening, you will see the following interface. Follow the prompts to pull the model.

When using webollama to pull the model, no progress is shown. Please wait patiently (it is recommended to use the above two methods to pull the model, as they allow you to monitor the progress).