Vritant Bhardwaj vritant24

VSCode Edu

Visual Studio Code for Education – https://vscodeedu.com

Educator Community – https://community.vscodeedu.com

Online course – https://learn.microsoft.com/en-us/training/modules/visual-studio-code-education-introduction

GitHub

Learning Plan: Understanding and Implementing LLMs (Large Language Models)

Audience: Software engineer with a computer science background
Goal: Learn modern LLMs on a technical and foundational level with practical implementation
Time Commitment: 1–2 hours/day
Approach: Mixed theory and coding, compact but deep plan
Focus: Free resources prioritized, including YouTube, articles, and open-access papers

A user’s project will be stored in the following way:

[folder] Project A
- [folder] metadata
	- [file] project.json
	- [file] file1.json
	- [file] file2.json
	...
- [folder] project_git (the git repo)

	using System;
	using System.Collections;
	using System.Collections.Generic;

	namespace Streamable
	{
	public class Sequence<T, U> : IEnumerable<T>, IEnumerator<T>
	{
	private readonly Func<T, U, ulong, (T element, U state, bool isLast)> formulae;
	private readonly T firstElement;

	using System;
	using System.Collections;
	using System.Collections.Generic;

	namespace Streamable
	{
	public class Sequence<T> : IEnumerable<T>, IEnumerator<T>
	{
	private readonly Func<T, ulong, (T nextElement, bool isLast)> formulae;
	private readonly T firstElement;

	for index, row in dataFrame.iterrows():
	if row[dataMeasure] == 'Projected Inventory':
	for str in list(my_dataframe.columns.values):
	pprint(str)

	// Implementation of the same neural network in Scala front end

	package lantern
	...

	def snippet(a: Rep[String]): Rep[Unit] = {
	...
	val train_loader = new DataLoader(...)

	// initialize all parameters

	# Adapt PyTorch implementation for our python front end

	from pylms import lms, stage, stageTensor # add our snek-lms module
	from pylms.rep import Rep # add our snek-lms module

	@lms # add anotation for snek-lms
	def run(dummy):
	...
	train_loader = torch.utils.data.DataLoader(...)

	# PyTorch implementation of 2 linear layers

	def run():
	...
	train_loader = torch.utils.data.DataLoader(...)

	class Net(nn.Module):
	def __init__(self):
	super(Net, self).__init__()
	self.fc1 = nn.Linear(784, 50)