Posts tagged with 'code'
-
Why Cross‑Entropy Still Rules Loss Functions
Negative log‑likelihood beats MSE for classification—here’s an intuitive recap
-
Exploring Two-Tower Ranking Models
Generating synthetic data and exploring the two-tower ranking model setup with Margin and InfoNCE loss
-
Fixing "Unknown at rule" warnings for Tailwind CSS in VSCode
How to resolve VSCode CSS lint warnings for Tailwind CSS at-rules by adjusting settings and installing extensions.
-
Key Concepts Behind QLoRA Fine-Tuning
Quantization + low-rank adapters let you fine-tune huge LLMs on a single GPU.
-
Relationship Between L1 Norm and L1 Regularization
Exploring how L1 and L2 norms form the basis of L1 (lasso) and L2 (ridge) regularization, with concrete examples and geometric intuition.
-
Why logits.exp() Equals Counts
Understanding neural network computations as log-domain operations, making multiplicative interactions additive through logs
-
Batch convert m4b to m4a with ffmpeg
Easily batch-convert .m4b audiobooks to .m4a for compatibility with apps like NotebookLM using ffmpeg on macOS.
-
Curse of Dimensionality
Why high-dimensional data quickly becomes sparse, distances stop making sense, and ML algorithms struggle
-
Dynamically Filtering Google Sheets with QUERY and Optional Criteria
How to build a dynamic Google Sheets QUERY that applies optional filters and supports multiple values using IN clauses.
-
Chain of Draft to Speed Up LLM Reasoning
Chain of Draft (CoD) prompts LLMs to use short, minimal reasoning steps, achieving near-CoT accuracy with far lower token use and latency.
-
FAISS vs pgvector - why one's a library and the other's a database
FAISS is a rocket-fast in-memory index, pgvector is Postgres with vectors. Here's when to pick each, with code.
-
What Does 'Ordinary' Mean in Ordinary Least Squares?
Why “ordinary” is used in OLS and how it distinguishes it from other least-squares methods.
-
Python's asyncio as a JS Dev
Some quick notes on Python's asyncio module coming from JavaScript.
-
Understanding Array Dimensions in NumPy
Clarifying what "dimension" really means in NumPy arrays and broadcasting.