Experience with Deepseek R1

Wow! WOW!  What a great Product Deepseek ! 

Why We got excited. The response from Deepseek. How i can share this with you all. or You also feel the excitement with the following Hands on.

Step 1:

go to ollama.com 

Download Ollama

Choose the model first to make sure your computer can handle it

Step 2: In terminal

    ollama run llama3.2

    ollama run deepseek-r (please chhose 7b Model)

Step 3: 

go to dockers.com 

Download docker desktop for your OS - Install - Minimize

In Terminal 

        ollama run OpenWebUI

Step 4:

Go to openwebui.com -> create accout 

Goto docs.openwebui.com - copy installtion script for docker (as shown below)

In Terminal 

docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:main

    Check ID  in Docker (desktop)

Step 5 :

Login to OpenWebUI, choose DeepSeek R1 from the model menu and start using your local AI chatbot.

https://openwebui.com/auth

Login

You will get Page like as shown below

Near Select a model, Click and add Deepseek and click + to add second Model :Llama3.2 (Just before we run or pull in Illama) as shown below:

Ok, Let us try some Chat in both model to compare llama3.2 and Deepseek-r1

 

Suppose you give a Query

Show me a code snippet of a website's sticky header in CSS and JavaScript.

The response will be like as shown Below: Just Watch! Watch Baby Watch !!!

In addition to that, it also provides a lot of chat 

So play  and Have Big Fun! with these parameters.

Also Provision for the merging above two responses using clicking icon the right corner bottom.

If you have doubts; Please refer for Playing

https://www.youtube.com/watch?v=5kFV20LatL8&t=606s (With Credits and Thanks)

https://www.youtube.com/watch?v=syR0fT0rkgY&t=3s for deployment