Vuk Rosić vukrosic

vukrosic / rmsnorm.ipynb

Last active October 21, 2025 21:26

RMSNorm Tutorial.ipynb

Sorry, something went wrong. Reload?

Sorry, we cannot display this file.

Sorry, this file is invalid so it cannot be displayed.

vukrosic / excercise.ipynb

Last active October 4, 2025 10:52

Implementing the NVFP4 Recipe From Scratch.ipynb

Sorry, something went wrong. Reload?

Sorry, we cannot display this file.

Sorry, this file is invalid so it cannot be displayed.

vukrosic / qwen3_from_scratch.ipynb

Last active October 19, 2025 17:05

qwen3_from_scratch.ipynb

Sorry, something went wrong. Reload?

Sorry, we cannot display this file.

Sorry, this file is invalid so it cannot be displayed.

vukrosic / inference_mnist_diffusion_image_gen.py

Last active August 7, 2025 12:33

Training and inference of image generation diffusion model for MNIST hand written digits

	# -- coding: utf-8 --

	import torch
	import torchvision
	import datasets
	import diffusers
	import accelerate
	from tqdm.auto import tqdm
	import matplotlib.pyplot as plt
	import os

vukrosic / t2vdiffusion.py

Last active August 5, 2025 18:43

Small text to video diffusion skeleton (generates 1 small video and overfits on it), build it from here

	"""
	Memory-Efficient Wan Text-to-Video Model - Single File Implementation
	Generates synthetic data, trains on it, and demonstrates inference
	Optimized for Google Colab with minimal GPU memory usage
	"""

	import math
	import torch
	import torch.nn as nn
	import torch.nn.functional as F

vukrosic / llm.py

Created August 5, 2025 10:42

Small transformer LLM

	import torch
	import torch.nn as nn
	import torch.nn.functional as F
	from torch.utils.data import Dataset, DataLoader
	from torch.cuda.amp import autocast, GradScaler
	import math
	import random
	import numpy as np
	from datasets import load_dataset
	from tqdm import tqdm

vukrosic / simple_neural_network.py

Created August 4, 2025 17:19

Simple neural network that fits a line and plots graphs for easier understanding

	import numpy as np
	import matplotlib.pyplot as plt

	class SimpleNeuralNetwork:
	def __init__(self, input_size, hidden_size, output_size, learning_rate=0.1):
	# Initialize weights and biases for 2-layer network
	self.W1 = np.random.randn(input_size, hidden_size) * np.sqrt(2.0 / input_size)
	self.b1 = np.zeros((1, hidden_size)) # Hidden layer bias
	self.W2 = np.random.randn(hidden_size, output_size) * np.sqrt(2.0 / hidden_size)
	self.b2 = np.zeros((1, output_size)) # Output layer bias

vukrosic / master-math-of-a-neuron-road-to-top-0-1-ai-researcher.ipynb

Last active November 9, 2025 07:11

master-math-of-a-neuron-road-to-top-0-1-ai-researcher.ipynb

Sorry, something went wrong. Reload?

Sorry, we cannot display this file.

Sorry, this file is invalid so it cannot be displayed.

vukrosic / StrawberryProductCard.tsx

Created July 5, 2024 12:40

Ecommerce product card - react (NextJS) code for this video - https://youtu.be/UObUvSu91PM

	"use client";

	import React, { useState } from 'react';
	import { Card, CardContent } from "@/components/ui/card";
	import { Button } from "@/components/ui/button";
	import { ChevronLeft, ChevronRight, Minus, Plane, Plus } from 'lucide-react';

	const product = {
	id: '1',
	name: 'Strawberries',