Shrinivasan Sankar

Chunking in Retrieval Augmented Generation (RAG)

In my previous article, we saw a comprehensive overview of Retrieval Augmented

Gone are those days of AI

This week I am taking a slight detour from my usual articles

Claude 3.5 Sonnet vs GPT-4o — An honest review

Anthropic the company behind Claude series of models has released Claude 3.

Comparing Kolmogorov-Arnold Network(KAN ) and Multi-Layer Perceptrons (MLPs)

We have taken the classic Multi-Layer Perceptrons (MLPs) for granted and built

XLSTM — Extended Long Short-Term Memory Networks

LSTMs or Long Short-Term Memory Networks have been around for a long

Make your LLM Fully Utilize the Context

A simple data-driven approach from Microsoft to increasing the context length of

Naive Quantization Methods for LLMs — a hands-on

LLMs today are quite large and the size of these LLMs both

Fine-tuning of LLMs - The six step lifecycle

Fine-tuning is an art and a methodical process similar to software engineering.

Retrieval Augmented Generation(RAG) — A quick and comprehensive introduction

LLMs have come a long way in the past year or so.

Lumiere — The most promising Text-to-Video model yet from Google

Would you like to see Monalisa smile like a witch? Or would

ControlNet — Take complete control of images from the generative model

This week let's look at one of the most influential

QLoRA — Train your LLMs on a Single GPU

In my previous article, we saw about Low-Rank Adaptation or LoRA. LoRA