My Courses
-
A Deep Dive into Federated Learning of LLMs
Federated Learning (FL) enables privacy-preserving training of Large Language Models (LLMs) across decentralized data sources, offering an ethical alternative to centralized model training.
-
DeepSeek-Prover-V2 for Mastering Mathematical Reasoning
DeepSeek-Prover-V2 combines informal reasoning and formal proof steps to solve complex theorems , achieving top results on benchmarks.
-
A Practical Guide to Enabling AI Agent Browser Control using Browser-use
Browser-Use is an open-source Python library that lets LLM-powered agents interact with websites via natural language, enabling real-world automation like job applications, research, and e-commerce.
-
Deep Dive into the First Scalable Native 1-Bit LLM BitNet b1.58 2B4T
BitNet b1.58 2B4T is the first native 1-bit, 2B parameter LLM trained on 4T tokens, matching full-precision models while drastically reducing memory, compute, and energy use.
-
Hands-On Guide to Implementing Multi-Agent Workflows Using LlamaIndex
In this hands-on guide, explore how to build a modular, intelligent multi-agent workflow using LlamaIndex. By combining OpenAI-powered agents with real-time tools and structured memory, you’ll learn to create collaborative systems that can research, write, and review complex tasks, unlocking the full potential of GenAI beyond single-prompt interactions.
-
Creating Web-Hosted Interactive Dashboards through Lovable
Build interactive, web-hosted dashboards effortlessly using Lovable without coding or complex tools.
-
Building GenAI-Based Dynamic Question Generator from Scratch
This article explores building a functional question generator using LangChain, Pydantic, Streamlit, and Python efficiently.
-
A Hands-On Guide to Building Multi-Agent Systems Using n8n
n8n is an open-source, low-code workflow automation platform that enables seamless integrations between applications using a visual, node-based system.
-
Deep Dive into Open Source RL for Large Scale LLMs DAPO
DAPO is an open-source RL framework that enhances LLM reasoning efficiency, achieving top-tier AIME 2024 performance with half the training steps.
-
A Hands on Guide to Compact Vision Language Models using SmolDocling
SmolDocling, a 256M VLM, enables efficient document conversion using DocTags to preserve structure while reducing computation.
