Source: author of the article

[rifat28dddd]

curl -fsSL https://ollama.com/install.sh | sh
Press Enter and wait for the installation script to complete. Now you can launch any model. This page contains a list of all models supported by Ollama. Let's take the codellama model as an example. Here is its separate page with all the necessary information. To launch it, you need to command:

ollama run codellama
After installing and running the model, we will see something like this:

After installing and running the model we will see something like this
Source: author of the article
The model invites us to send it a message. Judging by the description, this model should be good at code generation. Let's ask it to write a simple program. The terminal does not have syntax highlighting, so for clarity, we provide the text of the request and response outside the terminal.

Request text:

Write the source code of a button-press counter program in Python. The interface should have two buttons. One increases the number by one, and the other decreases it. Write the GUI in Tkinter.
And here is the neural network's response:

import tkinter as tk
class Counter ( tk.Tk ) :
def __init__ ( self ) :
super () . __init__ ()
self. title ( "Key Counter" )
self.button1 = tk. Button ( self, text= "+" , command=self.increment )
self.button1.pack ( )
self.button2 = tk. Button ( self, text= "-" , command=self.decrement )
self.button2.pack ( )
self.count = 0
self.label = tk. Label ( self, text=f "Count: {self.count}" )
self.label.pack ( )
def increment ( self ) :
self.count += 1
self.update_counter ( )
def decrement ( self ) :
if self.count > 0 :
self.count -= 1
self.update_counter ( )
def update_counter ( self ) :
self.label. config ( text=f "Counter: {self.count}" )
if __name__ == "__main__" :
Counter () . mainloop ()
Click on the "+" button to increase the number and on the "-" button to decrease it.
The neural network even left a short instruction manual for peru telegram data the program at the end. The program, by the way, is quite functional. This is what it looks like when running:

Keystroke counter
To run the program, you need to save the source code in any convenient place under some suitable name, for example, counter.py, and then command in the terminal:

python3 counter.py
To finish working with the model, just send a message with the text /bye. To delete an unnecessary model, you can use the rm command, for example:

ollama rm codellama
To update models, you can use the pull command:

ollama pull codellama
And to show a list of all installed models, we do this: