Hello world!

The first post on this English blog

Comments

Post a Comment

Popular posts from this blog

Solving mystery of LEGO Indiana Jones 2 green platform - part 1

Image
Hello everyone! This post will be very different than what I posted in this blog so far.  I hope to uncover an old LEGO Game mystery which hasn't been solved for more than a decade. I will also write some stuff on how LEGO Indiana Jones 2 works internally. I have talked about the topic with a friend who likes such stuff around half a year ago, but I didn't do anything more about that topic back then. Now I am going to look into the topic seriously with detail.  A video by channel EyeGuy inspired me to return to the topic. Thank you! I sadly have to split this into 2 parts, since I didn't manage to make any progress for too long but I want to publish something regardless. So, the thing I am going to look into is a mysterous green pad, which appears in last hub of LEGO Indiana Jones 2. The Kindom of the Crystal Skull part 3 one. The green pad in question The pad (I personally assume it is some sort of a landing pad) itself does not do anything in the game, people including me...
Read more

Pre-training a GPT-2 AI model on 32 GB of data. I made it both draw and recognise sketches!

Image
Hello everyone! In this post I will tell you about how I trained a GPT-2 "Small" AI model from scratch on a huge dataset of around 32 GB of raw text files with use of Torch and HuggingFace's Transformers libraries. I will explain steps of such a project, tell you about how it went for me and how I recommend doing these things now, and of course I will show you the code that pre-trains the AI model from a dataset too. Let's start from the beginning: 1. The idea, purpose and raw dataset First and foremost, a project like this needs an idea and should have an purpose. I pre-trained (trained from scratch) the AI model just to learn more about the process, but pre-training LLM AI models of that scale is done rarely and is usually pointless, as there are lot of base models already trained on specific languages that can then just be fine-tuned into a specific response format for example. But let's assume that we want to pre-train such an model anyway, for example as an a...
Read more

Project ISKRA - introduction

Hello everyone reading this blog! In this article, I will introduce you to my new long-term project - ISKRA. [Insert logo here once I get it] ISKRA means "spark" in Polish, it stands for Inteligentne Systemy Kontroli Robotów Autonomicznych. That translates to "Intelligent Systems of Autonomous Robots Control". But what is ISKRA and goals of the project? The answer is - to see how conversational artificial intelligence, such as for example ChatGPT; can deal with control of physical robots or digital bodies in different situations and with different tasks . The final goal is to create fully autonomous, intelligent systems capable of understanding and dealing with different tasks in different environments. This series of articles will be my experiment log, and some thoughts on how to achieve certain things. My articles related to it will not be professional scientific documents. I want them to be readable and understandable for everyone. Maybe once I get to some notewo...
Read more