馃嵄 Quick Bites 馃嵄

Small, digestible explorations of ML, math, and random curiosities.


Llama Token Embedding to Model Head Experiment

Does Same Token Encoded by embeder and then decoded by LM Head Yield Same Result?

8 min read 聽 路 聽 2024

Louvain Clustering

Maximize Modularity!

4 min read 聽 路 聽 2024

Induction as a Reduction

Generate or Reduce?

4 min read 聽 路 聽 2024

Two Envelope Problem

Switch or not to switch, that is the question.

5 min read 聽 路 聽 2024

Gender at Birth Ratio

Can people's preference affect gender at birth

6 min read 聽 路 聽 2024

Multinomial Pascal's Triangle

Pascal's triangle for multinomial coefficients

14 min read 聽 路 聽 2024

Convergence of Minimax complete Binary Tree

Part 1, Zero-sum game on a complete binary tree

8 min read 聽 路 聽 2024

Ranking Pokemon Types

Pokemon type ranking based on type effectiveness alone.

11 min read 聽 路 聽 2024

Bounds for Language Model Perplexity

What is perplexity in language modelling and the sensible bounds for it?

3 min read 聽 路 聽 2024