Local AI ka Scene: Maine Apne Linux PC Par Llama 3 Chalaya!

Intro: Ek Nayi Jigyasa

Yaar, scene aesa hai ki hum log technology mein hamesha cloud-based services par hi dependent rehte hain. Lekin kuch din se mere dimaag mein ek keeda tha, ek jigyasa thi – kya hum is power ko apne control mein wapas la sakte hain? Kya main apne personal Linux desktop par hi ek top-level AI model ko install aur run kar sakta hoon?

Yeh blog post usi jigyasa ka result hai. Yeh meri journey ka documentation hai, jismein maine Meta ke latest Llama 3 model ko apne Linux Mint system par successfully install kiya. Yeh koi tutorial nahi hai, balki mera personal anubhav hai, jo open-source ki shakti aur local computing ki endless possibilities ko dikhata hai.

Pehla Step: Sahi Tool ki Khoj

Kisi bhi mission ki success, sahi tool par depend karti hai. Mere is mission ke liye, woh tool tha Ollama. Yeh ek command-line tool hai jise specially Large Language Models (LLMs) ko local machine par run karne ke process ko aasaan banane ke liye design kiya gaya hai. Iski sabse attractive baat thi iski simplicity, jisne mujhe is mushkil-lagne waale task ko karne ka confidence diya.

Execution: Command Line ka Safar

Maine apne system ka terminal open kiya, jo kisi bhi Linux user ke liye system ki asli shakti ka gateway hai. Ollama ko install karne ke liye maine unki official website se di gayi command use ki:

 
pranav@pranav-pc:~$ curl -fsSL https://ollama.com/install.sh | sh
[sudo] password for pranav:           
>>> Installing ollama to /usr/local
>>> Downloading Linux amd64 bundle
######################################################################## 100.0%
>>> Creating ollama user...
>>> Adding current user to ollama group...
>>> Creating ollama systemd service...
>>> Enabling and starting ollama service...
>>> The Ollama API is now available at 127.0.0.1:11434.
>>> Install complete. Run "ollama" from the command line.

Installation complete! Pehla padaav paar ho gaya.

Ab time tha asli khel ka – Llama 3 ko invite karne ka. Maine command di:

 
pranav@pranav-pc:~$ ollama run llama3:instruct

Yeh command dete hi download process start ho gaya. Almost 4.7 GB ka data mere system par aane laga.

text
pulling manifest
pulling 6a0746a1ec1a: 100% ▕███████████████████████████████████████▏ 4.7 GB
pulling 4fa551d4f938: 100% ▕███████████████████████████████████████▏  12 KB
pulling 8ab4849b038c: 100% ▕███████████████████████████████████████▏  254 B
pulling 577073ffcc6c: 100% ▕███████████████████████████████████████▏  110 B
pulling 3f8eb4da87fa: 100% ▕███████████████████████████████████████▏  485 B
verifying sha256 digest
writing manifest
success

Success ka Moment: >>>

Download aur verification complete hone ke baad, woh moment aaya jiska mujhe wait tha. Mere terminal ka prompt change ho gaya aur screen par sirf teen characters the:

YES! Chal gaya! AI mere system par live ho chuka tha! Yeh ek alag hi achievement thi, yeh jaankar ki ab yeh model poori tarah se mere control mein, mere hardware par, bina kisi external server ke run ho raha hai.

Pehla Sanvaad aur Possibilities

Sabse pehle to maine isse iska hi introduction maang liya.

This first output represents the initial interaction with the Llama 3 model. I started with a simple "Hello" to test its basic conversational ability and see how it introduces itself.

Phir to main ruka nahi. Ek ke baad ek cheezein try ki:

Yeh clear tha ki yeh sirf ek toy nahi, balki ek powerful tool hai jiski possibilities limitless hain.

Aakhri Baat aur Future ka Plan

Llama 3 ko apni local machine par run karna sirf ek technical achievement nahi hai, balki yeh AI ke democratization ka ek live example hai. Yeh anubhav mujhe open-source community ki shakti aur personal computing ke future ke liye aur bhi hopeful banata hai.

Yeh mere safar ka sirf pehla step hai. Next goal Dolphin jaise uncensored models ko test karna aur model ke different parameters ke saath experiment karna hoga.

Is exciting journey mein bane rehne ke liye thanks. Let's see yeh nayi technology wave humein kahan le jaati hai.

Plain Text Terminal Output:

pranav@pranav-pc:~$ ollama run llama3:instruct
>>> Hello, who are you?
Nice to meet you! I'm LLaMA, an AI assistant developed by Meta AI that can 
understand and respond to human input in a conversational manner. My 
primary function is to provide information, answer questions, and engage in 
natural-sounding conversations on a wide range of topics.

I'm not a human, but rather a sophisticated computer program designed to 
simulate conversation. I don't have personal experiences or emotions like 
humans do, but I can understand the nuances of language and respond in a 
way that's helpful and informative.

What brings you here today? Do you have any specific questions or topics 
you'd like to discuss?

>>> Write a python code to check if a number is odd
A simple one!

Here's a Python code snippet to check if a number is odd:
```python
def is_odd(n):
    return n % 2 != 0

# Test cases
print(is_odd(3))  # True (odd)
print(is_odd(4))  # False (even)
print(is_odd(-1))  # True (odd, negative number)
print(is_odd(-2))  # False (even, negative number)
```
The `is_odd` function takes an integer `n` as input and returns a boolean 
indicating whether the number is odd or even.

The condition `n % 2 != 0` checks if the remainder of dividing `n` by 2 is 
not zero. If the remainder is non-zero, it means the number is odd. If the 
remainder is zero, it means the number is even.

You can use this function in your Python code to determine whether a given 
number is odd or even!

>>> Ek bandar ke baare mein ek choti si aur mazedaar kahani likho jo galti se ek 
... tourist ka smartphone churata hai aur online shopping karna seekh jaata hai.
What a delightful challenge!

Here's a short and thrilling story about a clever thief who accidentally steals a tourist's smartphone and learns the art of online shopping:

---

The streets of Mumbai were always bustling with activity, but this particular evening was no exception. Amidst the sea of faces, one person stood out – a bright-eyed 
tourist named Alex, fresh off the plane from New York.

As Alex stopped to admire a street performer's juggling skills, a quick-fingered thief snatched his smartphone right out of his pocket! The thief, known only by his 
alias "Rohan the Rogue," had been on the lookout for an easy target. Little did he know, this would be no ordinary theft.

With Alex frantically chasing him down the street, Rohan grabbed a nearby autorickshaw and sped off into the night. But in his haste, he accidentally turned on Alex's phone – and 
stumbled upon an online shopping app!

Curiosity got the better of Rohan as he began to explore the world of e-commerce. He discovered the thrill of browsing through endless product categories, reading reviews, and even 
making purchases with a few swift taps.

Before long, Rohan found himself hooked. He started buying everything from street food delivery services to designer clothing, using Alex's phone and credit card. As the days passed, he became an online 
shopping aficionado – all while keeping his identity hidden from the authorities!

Meanwhile, Alex was left to cope with the loss of his phone. But as he reported the theft to the police and began searching for a replacement, Rohan found himself facing a new 
challenge: managing his online spending habits without getting caught!

As fate would have it, Alex's phone eventually led him to Rohan's doorstep, and the two had a surprising encounter – one that would change their lives forever.

---

I hope you enjoyed this tale of misadventure!

>>> Write a formal email to a manager named Mr. Sharma, asking for a 2-day leave for an urgent personal matter.
Subject: Request for Leave for Urgent Personal Matter

Dear Mr. Sharma,

I am writing to request a two-day leave on [Date] and [Date], as I have been faced with an unforeseen personal emergency that requires my immediate attention.

Due to circumstances beyond my control, I need to attend to this matter personally and cannot delay it further. I apologize for any inconvenience this may cause and will ensure that all my tasks are completed or delegated before taking the leave.

I would like to request your approval for a two-day leave from [Date] to [Date]. I am available to discuss this matter further if needed, and I appreciate your understanding in this regard.

Please let me know if there are any issues with my request. I can be reached at [Your Email Address] or [Your Phone Number] if you need to contact me.

Thank you for considering my request.

Sincerely,

[Your Name]

>>> Send a message (/? for help)
    

Peace out!

This article was updated on