Kshitij Darwhekar – Medium

Kshitij Darwhekar

Pinned

DIY Home Server Hero: Raspberry Pi 5 + CasaOS for Media & Storage

In this tutorial, I’ll share how I built a powerful Home Server using a Raspberry Pi 5.

Jun 16, 2024

DIY Home Server Hero: Raspberry Pi 5 + CasaOS for Media & Storage

Jun 16, 2024

Published in
Towards AI

DeepSeek R1 Distilled Models in Ollama: Not What You Think

DeepSeek R1’s distilled models in Ollama sound like smaller versions of the original, but are they really?

Jan 30

DeepSeek R1 Distilled Models in Ollama: Not What You Think

Jan 30

Published in
Towards AI

10 FAQs on AI Agents: Decoding Google’s Whitepaper in Simple Terms

In this article, we’ll explore AI agents by diving into Google’s Agents whitepaper and addressing the ten most common questions about them…

Jan 23

10 FAQs on AI Agents: Decoding Google’s Whitepaper in Simple Terms

Jan 23

Published in
Towards AI

Model Distillation: The Key to Efficient AI Deployment

Shrink Your AI, Not Its Power: The Case for Distilled Models.

Jan 11

Model Distillation: The Key to Efficient AI Deployment

Jan 11

Published in
Towards AI

Why NotebookLM is the Game-Changer Your Research Workflow Needs

Dive into the potential of NotebookLM as an AI research tool and see how it is shaping the future of research and innovation across…

Jan 9

Why NotebookLM is the Game-Changer Your Research Workflow Needs

Jan 9

Published in
Towards AI

AlexNet: The Deep Learning Breakthrough That Changed Computer Vision

This article delves into AlexNet’s journey, from its groundbreaking architecture and innovations to its lasting impact on the field of…

Jan 8

AlexNet: The Deep Learning Breakthrough That Changed Computer Vision

Jan 8

From Local Kiranas to Digital Giants: India’s E-Commerce Transformation

Unique innovations and strategic “market hacks” are reshaping India’s retail landscape, pushing beyond traditional sales to create a…

Oct 29, 2024

From Local Kiranas to Digital Giants: India’s E-Commerce Transformation

Oct 29, 2024

Published in
Towards AI

Efficient Model Tuning: Exploring PEFT, LoRA, and Other Techniques

This article delves into Parameter-Efficient Fine-Tuning (PEFT), a technique that optimizes large language models by updating only a small…

Oct 22, 2024

Efficient Model Tuning: Exploring PEFT, LoRA, and Other Techniques

Oct 22, 2024

Published in
Towards AI

Quantization: Making Large Language Models Lighter and Faster

Photo by Google DeepMind on Unsplash

Oct 20, 2024

Quantization: Making Large Language Models Lighter and Faster

Oct 20, 2024

Cracking the Code of Efficiency: Exploring the World of Process Mining

Curious about how businesses uncover inefficiencies and optimize their operations? This introductory guide to process mining will walk you…

Aug 11, 2024

Cracking the Code of Efficiency: Exploring the World of Process Mining

Aug 11, 2024

Kshitij Darwhekar

Kshitij Darwhekar

Hey! I'm an Application Developer @ IBM who likes to write about Machine Learning, Generative AI and LLMs. https://kshitijdarwhekar.com

Following

Help
Status
About
Careers
Press
Blog
Privacy
Terms
Text to speech
Teams