TLDR 1. At a temperature of 1, the probability values are the same as those derived from the standard softmax function. 2. Raising the temperature inflates the probabilities of the less likely tokens, thereby broadening the range of potential candidates (or diversity) for the model’s next token prediction. 3. Lowering the temperature, on the other hand,...

Python GIL can’t guarantee thread safetyContinue reading on Towards Data Science »

One small step towards autonomous crater-based navigationContinue reading on Towards Data Science »

A user guide to mapping golf courses in Google Earth and bringing them to life in R.In the land of data viz, we are often inundated with bar, line, and pie charts. But it doesn’t have to be that way — in this article, I will demonstrate how to plot golf courses.Image by the authorIntroductionThere are close to 40,000 golf courses worldwide. If you are...

How Transformer architecture has been adapted to computer vision tasksContinue reading on Towards Data Science »

I’m Not Just Punching In Numbers At A Computer All DayPhoto by Myriam Jessier on UnsplashChoosing a college major was difficult for me. It felt like the first step to committing to a career and I wanted a little of everything. I liked math and programming, but I also wanted a job that allowed me to be creative, gave me a platform for communication,...