My Courses
-
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.
-
A Deep Dive into Chain of Draft Prompting
Chain of Draft (CoD) optimizes LLM efficiency by reducing verbosity while maintaining accuracy. It cuts token usage, lowers costs, and speeds up inference for real-world AI applications.
-
Mastering Multi-Head Latent Attention
DeepSeek’s MLA reduces KV cache memory via low-rank compression and decoupled positional encoding, enabling efficient long-context processing.
-
Building Agentic AI Applications using OpenAI Agents SDK
OpenAI’s Agents SDK enables efficient multi-agent workflows with context, tools, handoffs, and monitoring.
