DeepSeek-R1 Lands on Tencent Cloud, One-Click Deployment, 3 Minutes to Call

On February 2nd, Tencent Computer Systems Co., Ltd. of Shenzhen issued a statement announcing that the DeepSeek-R1 large model supports one-click deployment to Tencent Cloud’s “HAI”, allowing developers to access and call it within 3 minutes.

According to the official introduction from Tencent Cloud, developers can save the steps of buying cards, installing drivers, setting up networks, configuring storage, setting up environments, installing frameworks, downloading models and other steps through “HAI”, and can call the DeepSeek-R1 model in just two steps.

Create Deepseek-R1 application

Log in to Tencent Cloud HAI, click ‘Start Now’ to create a new DeepSeek-R1 application (first-time users need to follow the instructions to complete authorization).

After creation, developers can obtain the password through internal messages and choose to directly call it using a visual interface (ChatbotUI) or command line (JupyterLab).

Visualization interface calling method: Select “Computing Power Connection” in the “HAI” console -> “ChatbotUI”, and follow the instructions on the new window to operate.

Command line invocation method: In the ‘HAI’ console, select ‘Compute Connection’ -> ‘JupyterLab’, create a new ‘Terminal’, and enter the command ‘ollama run deepseek-r1’ to load the default 1.5b model.

If the 1.5B model does not meet your requirements, you can enter parameters such as 7B/8B/14B after the command line to freely switch to models of corresponding specifications.

SEE ALSO: DeepSeek Tops the Free App Charts in Both the US and China Apple Stores

Report