Large Language Models spend most of their decoding time not computing, but waiting: every new token requires reading all of the model weights from memory, only to multiply them by a single vecto...

Large Language Models are pushing the boundaries of artificial intelligence, but their immense size poses significant computational challenges. As these models grow, so does the need for smart o...

Training large language models either like GPT, LlaMa or Mixtral requires immense computational resources. With model sizes ballooning into the billions or sometimes even trillions of parameters...

In this post we will look at different techniques for steering LLMs behaviour to get desired outcomes, starting with some basic general principles such as writing a good prompt and ending ...

In recent years, the field of natural language processing has witnessed a remarkable breakthrough with the advent of Large Language Models (LLMs). These models have demonstrated unprecedented pe...

In 2022, insanely beautiful and original images created with generative neural networks are taking the internet by storm. This post focuses on the theory behind diffusion models that underpin th...

Few months ago, Kaggle launched featured simulation competition Kore-2022. In this kind of competitions participants bots are competing against each other in an game environment, supported by Kaggl...

This is the fourth and the last part of a ‘Visual Guide to Statistics’ cycle. All the previous parts and other topics related to statistics could be found here. In this post we will test hypoth...

A minimal condition for a good estimator is that it is getting closer to estimated parameter with growing size of sample vector. In this post we will focus on asymptotic properties of estimators...

Part II introduces different approach to parameters estimation called Bayesian statistics. Basic definitions We noted in the previous part that it is extremely unlikely to get a uniformly bes...