AI/ML
Deploying DeepSeek-R1 8B in Docker with Ollama: A Complete Setup Guide
Free Installation Guide - Step by Step Instructions Inside!
This amazing video explains DeepSeek AI Deployment.
Problem
You want to run Deepseek-r1 8B inside a Docker container for portability and isolation but are unsure about setting up Ollama within the container.
Solution
- Run the Docker container using Ollama's official Docker image.
- Pull and run Deepseek-r1 8B inside the container.
- Allow the container to interact with the host system for efficient execution.
1. Run the Ollama Docker container
Run the Ollama container using the following command
docker run -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollamaThis starts the container and exposes Ollama’s API on port 11434.
2. Logged in to the ollama container
Login into Ollama container by using docker exec command
docker exec -it ollama /bin/bashThis will log in to a docker container.
3. Pull the deepseek-r1 model
Inside the Ollama Container pull the required model of deepseek
ollama pull deepseek-r1:8b This will pull the all dependencies of the model
4. Run the model
Now run the pulled model by using the following command.
ollama run deepseek-r1:8b
Now the model will run in interactive mode you can test with any prompt you want to test.
>>>Hello!5. Run ollama web gui container
Run the ollama web gui container using the following command. You need to change <YOUR-IP> filed with your local IP address.
docker run -d -p 3000:8080 -e OLLAMA_BASE_URL=http://<YOUR-IP>:11434 -vopen-webui:/app/backend/data --name open-webui --restart alwaysghcr.io/open-webui/open-webui:main
Now open your browser, and hit the URL “http://<YOUR-IP>:3000” and start to interact with the deepseek model.Conclusion
Running Deepseek-r1 8B in a Docker container provides portability, isolation, and easy deployment across multiple environments. You can now interact with the AI model using local commands or API requests.
Ready to transform your business with our technology solutions? Contact Us today to Leverage Our AI/ML Expertise.
Comment