Data Structures: Arrays
How arrays work one level below the usual abstractions, from RAM layout to Two Sum
Notes from my studies and thoughts in between.
How arrays work one level below the usual abstractions, from RAM layout to Two Sum
LayerNorm centers and scales, RMSNorm only scales. A geometric explanation shows why centering is dispensable without losing model quality.
transpose() makes tensors non-contiguous (logical ≠ physical order). view() only works with contiguous tensors → RuntimeError. Solution: use reshape() instead of view().
How I fine-tuned a LLAMA 3.1 model on Swabian — data preparation, QLoRA training, and evaluation from the real world.
A beginner-friendly guide to neural networks: from individual neurons to a complete Python model that predicts house prices using NumPy.
An introduction to linear regression: model definition, cost function, and gradient descent, explained with a simple example of students and their study hours.