I have been pretty careless with keeping track of the code I write for my blogs.
So I thought of creating a repository to keep track of all the code that I end up writing for my blog posts.
Although there are a lot of other blog posts which don't have codes here. So, follow me up at Medium blog @mlwhiz .
Each series has its own repo. Code links point to the folder for that post. The ML Careers posts have no code, so they link to a written summary.
#
Post
Blog
Code
1
RecSys Fundamentals: The Art and Science of Digital Matchmaking
Blog Code
2
How Recommendation Systems Learned to Think
Blog Code
3
The 3-Stage Funnel Behind Every Modern Recommender System
Blog Code
4
How YouTube Finds Your Next Video in Milliseconds
Blog Code
5
Vector Search at Scale: The Production Engineer's Guide
Blog Code
6
From Candidates to Clicks: The Engineering Anatomy of Ranking
Blog Code
7
3 Modern Approaches to Solving Cold Start in RecSys
Blog Code
8
Your Ranking Model Is Right. Your Recommendations Are Wrong
Blog Code
9
From RNNs to Transformers: Building Sequential Recommenders (Part 1)
Blog Code
10
From Random IDs to Semantic IDs: Building a Generative Recommender from Scratch
Blog Code
11
HSTU: How Meta Built a Trillion-Parameter Recommender That Actually Scales
Blog Code
12
HSTU From Scratch in PyTorch - A complete Walkthrough
Blog Code
#
Post
Blog
Code
1
Understanding Transformers, the MLE Way
Blog Code
2
The Transformer, Demystified: Let's Actually Build One
Blog Code
3
What is an LLM? Tokens, Embeddings, and the Big Picture
Blog Code
4
Pretraining 101: Data, Scale, and the Loss Function
Blog Code
5
Post-Training 101: From Base Model to Assistant
Blog Code
#
Post
Blog
Code
1
GenAI Series: A Review of the Architectural Journey
Blog Code
2
GenAI Series: The Art and Science of Prompt Engineering
Blog Code
3
GenAI Series: My Tryst with AI-Assisted Development
Blog Code
4
GenAI Series: Building RAG Applications
Blog Code
5
Advanced RAG Techniques for ML Engineers: Beyond Vector Search
Blog Code
6
Advanced PEFT Techniques for Model Fine-tuning
Blog Code
7
Traditional RAG is Dead, Long Live GraphRAG
Blog Code
8
Why LLMs Won't Replace Programmers: A Reality Check
Blog Code
9
GenAI 101: How Generative AI is Rewriting the Rules for ML Engineers
Blog Code
10
Did Apple Just Burst the AI Reasoning Bubble? I don't think so
Blog Code
11
Which AI Subscription is Actually Worth Your Money?
Blog Code
12
The #1 Reason Your GenAI Project Will Fail in Production (and the 4 Pillars to Prevent It)
Blog Code
13
What Production Deployments Taught Me About ReAct vs Function Calling
Blog Code
14
I Use Claude Code Every Day. Here's the Setup That Actually Matters
Blog Code
15
5 Things Meta Muse Actually Does, and the Engineering Behind Each One
Blog Code
Older posts (code in this repo)
Deep Learning
BlogLink
CodeLink
An End to End Introduction to GANs
Blog Code
Faster and Memory-Efficient PyTorch models using AMP and Tensor Cores
Blog Code
Chatbots aren’t as difficult to make as You Think
Blog Code
End to End Multiclass Image Classification Using Pytorch and Transfer Learning
Blog Code
Using Deep Learning for End to End Multiclass Text Classification
Blog Code
Object detection using mask-RCNN on custom Dataset
Blog Code
The Most Complete Guide to PyTorch for Data Scientists
Blog Code
A Layman's Introduction to GANs for Data Scientists using PyTorch
Blog Code
Understanding Transformers, the Programming Way
Blog Code
How to Create an End to End Object Detector using Yolov5
Blog Code
Data Science
BlogLink
CodeLink
Applications of MCMC for Cryptography and Optimization
Blog Code
Advanced Streamlit Caching
Blog Code
A Newspaper for COVID-19 — The CoronaTimes
Blog Code
Minimal Pandas Subset for Data Scientists on GPU
Blog Code
How to run your ML Predictions 50 times faster?
Blog Code
How to write Web apps using simple Python for Data Scientists?
Blog Code
Using Gradient Boosting for Time Series prediction tasks
Blog Code
Lightning Fast XGBoost on Multiple GPUs
Blog Code
How to use SQL with Pandas?
Blog Code
A Layman's Guide for Data Scientists to create APIs in minutes
Blog Code
Deployment could be easy: A Data Scientist's Guide to deploy an Image detection FastAPI API using Amazon ec2
Blog Code
BigData
BlogLink
CodeLink
4 Graph Algorithms on Steroids for data Scientists with cuGraph
Blog Code
5 Ways to add a new column in a PySpark Dataframe
Blog Code
100x faster Hyperparameter Search Framework with Pyspark
Blog Code
The Hitchhikers guide to handle Big Data using Spark
Blog Code
The Most Complete Guide to pySpark DataFrames
Blog Code
