Blog

Articles and thoughts on AI, Machine Learning, and Software Engineering

SK

Adithya S Kolavi

AI Researcher, Building Generative AI solutions at Scale

Building AI that actually works! Currently deep into Vision-Language Models and Agentic Systems, with hands-on experience taking AI projects from wild ideas to real products. Love tinkering with model fine-tuning and cloud deployments. Big open-source enthusiast - you'll find me contributing to projects that make AI more accessible to everyone.

2025-01-1015 min read
External

Building Ambari-7b: India's First Kannada-English Bilingual LLM

The technical journey of creating a performant bilingual LLM for low-resource languages with limited training data.

Low-Resource Languages
LLM Training
Bilingual Models
2024-04-1910 min read
External

From 7B to 8B Parameters: Understanding Weight Matrix Changes in LLama Transformer Models

Deep dive into the underlying architecture of LLama3 and the structural changes between 7B and 8B parameter models.

LLMs
Model Architecture
Transformers
LLama
2024-04-157 min read
External

Axolotl is all you need

A low-code guide to fine-tuning LLMs efficiently using the Axolotl library.

Fine-tuning
Axolotl
LLMs
2024-02-2115 min read
External

A Beginner's Guide to Fine-Tuning Gemma

A comprehensive guide to fine-tuning Google's Gemma model with practical examples and best practices.

Gemma
Fine-tuning
Google Models
2024-01-0814 min read
External

A Beginner's Guide to Fine-Tuning Mixtral Instruct Model

Unleashing the power of Mixtral: A comprehensive guide to fine-tuning this powerful mixture-of-experts model.

Mixtral
MoE
Fine-tuning
LLMs
2024-01-018 min read
External

Run any Huggingface model locally

A practical guide and colab notebook to quantize LLMs in GGUF format to run them efficiently on your local machine.

GGUF
Quantization
Local Deployment
Hugging Face
2023-10-219 min read
External

Squeeze Every Drop of Performance from Your LLM with AWQ

A guide to quantizing LLMs using Activation-Aware Quantization (AWQ) on a Google Colab notebook for optimal performance.

AWQ
Quantization
Model Optimization
Colab
2023-10-0810 min read
External

Deploy Mistral/Llama 7b on AWS in 10 mins

A step-by-step guide to deploying Mistral or Llama models on AWS in just three simple stages.

AWS
Deployment
Mistral
Llama
Cloud
2023-10-0616 min read
External

A Beginner's Guide to Fine-Tuning Mistral 7B Instruct Model

Fine-tuning the Mistral 7B model for code generation using a single Google Colab notebook.

Mistral
Fine-tuning
Code Generation
Colab
2023-09-1511 min read
External

CompanionLLama: Your AI Sentient Companion

A journey into fine-tuning LLama2 to create an AI companion with personality and conversational abilities.

LLama2
AI Companion
Fine-tuning
Personalization