Zero to Neuron Series 9: Vision Transformer by Hand: Every Number, Every Matrix, Every "Why"A complete numerical walkthrough for CNN practitioners stepping into the world of Transformers — from raw pixels to final class probabilities, with no hand-waving allowed. You've studied CNNs. You knMay 12 · 35 min readimportarun-dl.hashnode.dev
Zero to Neuron Series 8: The Goldilocks Dilemma—Overfitting, Underfitting, and TuningWe've done the analogies. We've done the math. We've even made the GPU sweat. But here is the hard truth about Machine Learning: Just because your model runs, doesn't mean it’s learning. A model is liFeb 15 · 7 min readimportarun-dl.hashnode.dev
Zero to Neuron Series 7: Evaluation Metrics in Machine Learning: The Ultimate GuideWe’ve built the models. We’ve cleaned the data. We’ve tuned the hyperparameters until our GPUs cried for mercy. But here is the uncomfortable question: Is the model actually any good? You can’t improvFeb 15 · 9 min readimportarun-dl.hashnode.dev
Zero to Neuron Series 6: Coding QLoRA - Fine-Tuning an LLM on a Single GPUWe've done the analogies. We've done the math by hand. Now, it's time to make the GPU sweat. Welcome to the most practical post in the series! We're going to take all that theory from Series 4 and 5 and turn it into working Python code. Our goal: To ...Nov 1, 2025 · 11 min readimportarun-dl.hashnode.dev
Zero to Neuron Series 5: QLoRA By Hand — A Step-by-Step Numerical WalkthroughWelcome back, data adventurers, to the final boss of our fine-tuning series! In our last post, we learned the "what" and "why" of QLoRA. We saw how it combines Quantization (shrinking the model) with LoRA (adding a tiny "cheat sheet") to let us fine-...Nov 1, 2025 · 8 min readimportarun-dl.hashnode.dev
