Install AI Server in Hindi and forget ChatGPT🔥 Llama3
Contact :- [email protected]
Best AI website builder creates it for you — fast, simple, and stunning.
Click the link in bio: hostinger.in/horizons?REFERRALCODE=OPCPATHANDY4
It’s the easiest way to get online.
--------------------------------------------------------------------------------------------------------------------------------------------
To Learn Linux course use following link:-
https://www.udemy.com/course/linux-ze...
-------------------------------------------------------------------------------------------------------------------------------------------------------
Introduction :
In this video, I guide you through the process of installing and running multiple Large Language Models (LLMs) using Ollama, including Llama 3, Gemma 2, and OpenWebUI. Whether you're new to AI or an experienced developer, this step-by-step tutorial will help you get these powerful models up and running on your own machine. Perfect for anyone looking to experiment with the latest in AI technology, this video covers everything you need to know to start using these LLMs effectively. Don't forget to like, comment, and subscribe for more AI tutorials and tech insights!
For Training and Queries Email Us: [email protected]
#ai #tech #technology #hindi #technicalguruji #linux #ollama #llm #chatgpt #openai #meta #windows #wsl #ubuntu #hinditech #indiatech #server #techyoutuber #iit #operatingsystem #installation #informationtechnology #aimodel #virtualization #virtualmachine #automation #indiatech #siliconvalley #betech #techcommunity #aicommunity
---------------------------------------------------------------------------------------------------------------------
Prerequisite :-
Only for Windows User :- Either install WSL or create a Virtual Machine follow below videos
How to install and manage WSL
Link:- • Windows on Linux and Linux on Windows WSL2...
How to install and manage Virtual Machine
Link:- • Virtualization Explained: How to Install V...
MAC user :- All Good
Linux user :- All Good
-------------------------------------------------------------------------------------------------------------------
Step-by-Step Guide: Installing Ollama on WSL2 with Gemma2 & Llama 3.1 | Open WebUI Setup with Docker & User Permissions
Installation :-
1. Install WSL for Windows only.
WSL --install
2. Update ubuntu in WSL, VM or Update Mac
sudo apt update
sudo apt upgrade -y
3. If Using NVIDIA graphic card install CUDA Widnows and Linux.
https://developer.nvidia.com/cuda-dow...
4. Install Ollama setup as per your OS Mac, Linux or Windows from https://ollama.com/
Note :- If your server/workstation have GPU it should automaticially detect GPU if not install CUDA for linux from NVIDIA website.
5. Test in browser localhost:11434
Ollama is running
Ollama API services works on port 11434
6. Download AI model from Ollama website
ollama run llama3.1:8b
ollama run gemma2:2b
7. Prompt some question and check CPU and GPU performance
Watch -n 0.5 nvidia-smi
8. Install Docker
https://docs.docker.com/engine/instal...
10. Install Open-UI in Docker Container
sudo docker run -d --network=host -v open-webui:/app/backend/data -e OLLAMA_BASE_URL=http://127.0.0.1:11434 --name open-webui --restart always ghcr.io/open-webui/open-webui:main
11. Open a browser
localhost:8080
12. Create a Account and login first account login will become admin
13. After login check if installed models are connected with Open WebUI. To check you can navigate to settings see Ollama base URL is there.
14. Now chat with installed AI models and you have a local LLM AI installed on your PC/Server.
Topics Covered:
ai llm course
introduction to llm
introduction to large language models
chatgpt type ai
free ai tools like chatgpt
ollama webui
ai courses for beginners
ai course in hindi
generative ai