Effortlessly Deploying DeepseekR1 with Ollama

Introduction

Deploying the DeepseekR1 model locally on your computer can be a rewarding experience, allowing you to leverage the power of Natural Language Processing (NLP) right from your own machine. The DeepseekR1 model is part of the Ollama ecosystem, a free and open-source platform that facilitates running NLP models locally. The model ranges from the 1.5b version with 1.1GB storage to the 671b version with 404GB storage. Follow these steps to achieve the desired setup.

Steps to Deploy DeepseekR1

Step 1. Go to Google Search and type “Ollama” in the search bar.

Step 2. Click on the first link, "Ollama," and you’ll find the following page.

Step 3. Based on your preference, select a download option (for example, Windows).

Step 4. Click on Models. Here, you can see numerous models, including DeepseekR1.

Step 5. To ensure the successful installation of Ollama, open the command prompt and type Ollama help.

Step 6. Verify the respective storage by using the command ollama pull deepseek-r1:1.5b.

Step 7. After entering the command, it will pull all available resources and display a successful message in the prompt.

Step 8. To execute your prompt, use the command ollama run deepseek-r1:1.5b. The prompt will display a "send a message" draft.

Step 9. Enter your prompt in the "send a message" draft and press enter. You will see the output below.

Conclusion

By following these straightforward steps, you can successfully deploy the DeepseekR1 model on your computer using Ollama. This setup enables you to run advanced NLP models locally, unlocking a world of possibilities in natural language understanding and processing.