Fareed Khan Claim this profile

A straightforward method for training your LLM, from downloading data to generating text.

A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

35 production-grade agentic AI architectures (Reflexion, LATS, GraphRAG, MemGPT, Voyager, BrowserAgent, ...) — a Python library and runnable textbook with multi-provider LLM support and a 17-task benchmark leaderboard.

Implementation of all RL algorithms in a simpler way

Core 7 layers of production grade agentic system

Building DeepSeek R1 from Scratch

A step by step implementation of a complex RAG pipeline to solve real world situations

Building a Multi-Agent AI System with LangGraph and LangSmith

9 Different Ways to Optimize AI Agent Memories

Converting Unstructured Data to a Knowledge Graph: An End-to-End Pipeline

23 Components of the Claude Code Architecture

Understand and code every important component of RAG architecture

Agentic RAG to achieve human like reasoning

In this blog, we will build a small scale text-to-video model from scratch. We will input a text prompt, and our trained model will generate a video based on that prompt.

Self improving agentic rag pipeline

Building a 2.3M-parameter LLM from scratch with LLaMA 1 architecture.

LLaMA 3 is one of the most promising open-source model after Mistral, we will recreate it's architecture in a simpler manner.

A scalable RAG platform combining LangGraph agents, hybrid retrieval (Vector+Graph), and Ray orchestration on Kubernetes.

Agentic RAG, Multi-Agent Systems, and Vision Reasoning are three pipelines to find the perfect LLM

Handling 10M+ docs using RAG with zero hallucinatons

A Deep Thinking RAG Pipeline to Solve Complex Queries

Implementation of Deep Thinking Trading System

Core concepts - where to apply parallelism in agentic solution

Implementation of contextual engineering pipeline with LangChain and LangGraph Agents

Maximizing the Performance of a Simple RAG using RL

Optimizing Dynamic Knowledge Base Using AI Agent

Implemented a stable diffusion architecture using PyTorch.

LLM Based NLP Library.

Some words that LLM regularly uses

A Straightforward, Step-by-Step Implementation of a Video Diffusion Model

Building a Senior Staff Engineer with Sub-Agent Teams in Claude Code

A Step-by-Step Implementation of Qwen 3 MoE Architecture from Scratch

A Step-by-Step Implementation of Google Veo 3 Architecture from Scratch

Building LLaMA 4 MoE from Scratch

Implementation of a GPT-4o like Multimodal from Scratch using Python

Training architecture for self-improving AI agents.

Building a Tiny GPU to understand AI hardware engineering

Different Types of Prompt Engineering Techniques

AI agent that controls a computer

Building a Production-Grade MCP Server Architecture with a Multi-Agent System

Building a Claude-like agentic system.

A detail Implementation of handling long-term memory in Agentic AI

No description.

A multi-agent system trained with GRPO for reliable long-horizon task planning and execution.

Deep research agentic system using Time Test Diffusion

Train a 29M parameter GPT from Scratch

Implementation of 12 AI agents evaluation techniques

Layered guardrails to make agentic AI safer and more reliable.

Improving langchain knowledge graphs using baml

An 18 notebook course that isolates and measures each component of agentic loop engineering on real, industry standard software datasets.

GLM-5.2, a 744 billion parameter mixture of experts model, in a pure C inference engine: quantized to int4, experts streamed from disk, deployed and benchmarked. Generates in 16 GB of RAM.

A Step-by-Step Implementation of RAPTOR based RAG implementation

A step by step implementation to build an agent that runs for week to complete a task and self improve.

Understanding Large Language Transformer Architecture like a child

An end-to-end pipeline to optimize and host LLM for 100K parallel queries

Gemini, as capable as GPT-4, provides a free API with limited access. I tested it with the help of prompt engineering and found that it can solve almost any NLP task you want to tackle.

Encountering 14 different Naive RAG fails and using KG to solve it

An automated Python tool that uses LLMs and internet to automatically fix your code until it runs perfectly.

Handling Big Data with Knowledge Graph: A Detailed Guide

This web application is designed to facilitate seamless communication with the Gemini API, and it's available for free.

Building an advanced Agentic eCommerce WhatsApp bot

A straightforward method to reduce your LLM inference API costs and token usage.

A step by step implementation of building an AI agent that plays 3d shooting game

Forty hands-on recipes for production-grade retrieval-augmented generation, Nebius-first and provider-agnostic.

Contextual Engineering Pipeline

A Curated Collection of LLM resources (work in progress).

From-scratch reimplementation of Google TimesFM (time-series foundation model) plus the full pretraining pipeline Google never open-sourced. Trained and honestly evaluated at 70M.

A step by step implementation of a complex AI Evaluation System Designing

A Beginner's Guide to Monetizing Your Python AI Chatbot

A straightforward explanation of how DeepSeek R1 works

Reverse Engineering of the Mythos Architecture — What I Think

End-to-end agentic quantum-ML pipeline: PennyLane GPU quantum-kernel anomaly detection + LangGraph multi-agent system + locally-hosted Qwen3-14B, benchmarked across network-intrusion, LHC physics, and fraud.

Generating diverse and realistic datasets for computer vision training using AI.

Talking Graphs: Your Data Speaks Up

Intelligent Help for Efficient Programming

26 different problems dev teams faces with Git

Evolving LangChain agent architectures using the Quality-Diversity (QD) algorithm.

Outlier Detection with AI + ML

We have listed some of the free and powerful GenAI APIs and explore their benefit and usage.

This repository is created on top of two repositories i.e., yolov7 face detection and yolov7 blurring object

An autonomous agentic pipeline that finds, proves, and patches real C memory-safety vulnerabilities end-to-end using a single 7B open-source LLM (Qwen2.5-Coder) on vLLM, with AddressSanitizer as a ground-truth oracle.

Config files for my GitHub profile.

This project focuses on generating a diverse and realistic dataset for computer vision training using ChatGPT and a realistic vision image generation model. The process involves dynamically creating prompts, utilizing ChatGPT to generate image descriptions, and generating images based on those descriptions.

Benchmarking RAG and agentic systems in Go vs Python

A Classification Approach: Making LLM Knowledge-Aware

Using the OpenAI Gym library, I implemented two reinforcement learning algorithms in the Frozen Lake environment.

This repository provides a PyTorch implementation of a video diffusion model, similar to OpenAI's Sora, allowing you to train and generate videos from text prompts using a configurable architecture and diffusion process.

transformer again in the same manner as I did in my previous blog (for both coders and non-coders), providing a complete guide with a step-by-step approach to understanding how they work.

Learn about the fundamentals of LangGraph through a series of notebooks

DigiArt is a powerful AI image generator built on top of Stable Diffusion. This repository offers a free demo utilizing Clipdrop for non-commercial use, allowing users to generate stunning digital artwork.

A multi-layered, open-weight system for catching malicious AI agents from their own transcripts.

After RLHF and SFT show promising results, a new technique named SPIN is invented for 2024

An agentic exploitation-evaluation harness: grade whether a coding agent can turn a known bug into an exploit, and contain it while it tries.

The original data contains 500k conversations, but this is just a sample. You can download the 10k dataset with personal and sensitive information removed.

This repository hosts a diverse NLP dataset comprising 1,000 stories spanning 100 genres for comprehensive language understanding tasks.

A collective list of free APIs

Speed up your RAG by performing cosine similarity parallel on your CPU Cores

Strategies to significantly reduce your OpenAI API costs.

Develop a Streamlit interface to showcase similar items from a knowledge base using various techniques like Bag of Word, pre-trained Word2Vec, GLoVe embeddings, customized Word2Vec, and SVD/LSA Embedding, while conducting extensive experimentation to determine optimal parameters.

This app uses the GenerativeAI library to correct spelling mistakes in the input text.

Generate Excalidraw diagrams from Mermaid

Vellum: an auditable agentic ICD-10-CM/PCS autocoder that proves every code and catches the model fabricating its own evidence. Glass-box web cockpit. Built with Claude.

An adaptable, open-source context-aware inference engine designed for privacy, control, and independence from proprietary models.

No description.

No description.

A simple, clean and responsive portfolio website for developers to showcase their projects. Live-Preview-Link-For-The-Website: https://fareedkhan-dev.github.io/Responsive-Portfolio-Website/

An AI Coding Agent Powered by LangGraph

No description.

Examples and guides for using the OpenAI API

This repository delivers end-to-end, code-first tutorials covering every layer of production-grade GenAI agents, guiding you from spark to scale with proven patterns and reusable blueprints for real-world launches.

This project is done using Python library NetworkX, which helps us to analyze the GitHub Social Network Data.

This project is based on docker image of apache hive, showing all the basic commands to understand hive queries.

MS Data Science Social Network Analysis Project

No description.

This repo contains single jupyter notebook file which contains all the code

Curated list of design and UI resources from stock photos, web templates, CSS frameworks, UI libraries, tools and much more

GenAI Processors is a lightweight Python library that enables efficient, parallel content processing.

No description.

PDF text data extraction web app with OCR for scanned documents

Building a 2.3M-parameter LLM from scratch with LLaMA 1 architecture.

No description.

This project analyzes and generates new names using various techniques and neural networks.

A Python implementation of John Gruber’s Markdown with Extension support.

Amazing 3d games in Python

No description.

No description.

No description.

Code Synonyms Do Matter: Multiple Synonyms Matching Network for Automatic ICD Coding [ACL 2022]

This project is for 2024 AI Competition by Team name Zevar

No description.

Created a Flask application that uses the GPT API to build a chatbot. The chatbot can generate responses based on user input using the GPT language model.

this is repo for github codespace

No description.

No description.

This is a blog written for ML-2 Project i.e, Analysis of Distribution-based Clustering Methods

APReL: Active preference-based reward learning for human-robot interaction. Utilizing "Mountain Car" environment, learn from human preferences to reach the goal state. Applications in robotics and adaptability to other learning methods.

My own profile created with gitprofile repository

This project is based on two mini projects. First one is telling the client information. Second one is sending the mail which contains a unique ID for the user.

View the live preview here: https://fareedkhan-dev.github.io/facebook-login-page-ui/

cuML - RAPIDS Machine Learning Library

PLM-ICD: Automatic ICD Coding with Pretrained Language Models

No description.

No description.

this is a frontend of digiart webui

No description.

This project will help you integrate stackoverflow profile on your portfolio website

No description.

This repository uses TensorFlow and Keras to classify clothing items. It includes a simple neural network model for image classification of shirts, pants, shoes, and trousers. The code provides dataset loading, preprocessing, model training, and evaluation. It's a beginner-friendly resource for clothing classification using TensorFlow and Keras.

No description.

Competition took place IBA University (Machine Learning Classification Problem) Predicting the load type

No description.

Sample Flask Application to be deployed on DigitalOcean's App Platform

No description.

an opinionated npm package initializer

No description.

No description.

Config files for my GitHub profile.

Google/Bing Images Web Downloader

No description.

No description.

No description.

Collection of Summer 2023 tech internships!

No description.

No description.

No description.

No description.

No description.

No description.

No description.

No description.

No description.

No description.

No description.

Ruby blogging site

No description.

No description.

No description.

No description.

No description.

No description.