My Writing

Fine-tuning a 3B Model for Transcript Analysis: Better Than 70B Models?

How I fine-tuned Llama 3.2 3B to process transcripts locally, achieving better results than models 5-8x larger through specialized training.

Posted on September 1, 2025

ToddlerTones: an offline, toddler‑proof soundboard with a gentle ‘Find it’ game

Designing and building a distraction‑free Android app in Kotlin/Compose with low‑latency audio and a guided vocabulary mode.

Posted on August 26, 2025

All-in-1 AI Tutor: Processing a Wikipedia Article Just Once

Exploring a single-LoRA, tag-routed architecture that processes a Wikipedia article once and generates study guides and concept maps/timelines.

Posted on August 3, 2025

Democratizing Education: An AI Tutor for Every Child

A plan to build a small local offline AI tutor for children in underserved communities.

Posted on Jul 28, 2025

Reluctant Buddha: Fine-Tuned LLM for shitty insights

Turning a 1B LLM into a deranged cosmic entity running on CPU only.

Posted on Mar 08, 2025
Bilawal.net

© 2025

𝕏 GitHub