

<feed xmlns="http://www.w3.org/2005/Atom">
  <id>https://int8.io/</id>
  <title>Int8</title>
  <subtitle>Int8 - about machine learning.</subtitle>
  <updated>2026-03-09T12:20:58+01:00</updated>
  <author>
    <name>Kamil</name>
    <uri>https://int8.io/</uri>
  </author>
  <link rel="self" type="application/atom+xml" href="https://int8.io/feed.xml"/>
  <link rel="alternate" type="text/html" hreflang="en"
    href="https://int8.io/"/>
  <generator uri="https://jekyllrb.com/" version="4.4.1">Jekyll</generator>
  <rights> © 2026 Kamil </rights>
  <icon>/assets/img/favicons/favicon.ico</icon>
  <logo>/assets/img/favicons/favicon-96x96.png</logo>


  
  <entry>
    <title>My Adventure With Team Ball Action Spotting Task at SoccerNet Challenge 2025</title>
    <link href="https://int8.io/team-ball-action-spotting-challenge-2025" rel="alternate" type="text/html" title="My Adventure With Team Ball Action Spotting Task at SoccerNet Challenge 2025" />
    <published>2025-05-23T00:00:00+02:00</published>
  
    <updated>2025-05-24T12:03:00+02:00</updated>
  
    <id>https://int8.io/team-ball-action-spotting-challenge-2025</id>
    <content type="text/html" src="https://int8.io/team-ball-action-spotting-challenge-2025" />
    <author>
      <name>Kamil</name>
    </author>

  
    
    <category term="Computer Vision" />
    
    <category term="Machine Learning" />
    
    <category term="SoccerNet" />
    
  

  <summary>My journey with the SoccerNet Team Ball Action Spotting Task at SoccerNet Challenge 2025, from zero knowledge to building a refined T-DEED model using tailored augmentations, training strategies, and effective post-processing to achieve test server winning solution (challenge dataset results to be announced on CVPR 2025)</summary>

  </entry>

  
  <entry>
    <title>Train your own South Park Fanatic AI with Mistral-7B</title>
    <link href="https://int8.io/train-your-own-south-park-fanatic-ai-with-mistral-7b/" rel="alternate" type="text/html" title="Train your own South Park Fanatic AI with Mistral-7B" />
    <published>2023-10-23T00:00:00+02:00</published>
  
    <updated>2025-05-24T07:43:41+02:00</updated>
  
    <id>https://int8.io/train-your-own-south-park-fanatic-ai-with-mistral-7b/</id>
    <content type="text/html" src="https://int8.io/train-your-own-south-park-fanatic-ai-with-mistral-7b/" />
    <author>
      <name>Kamil</name>
    </author>

  
    
    <category term="Large Language Models" />
    
  

  <summary>The purpose of this blog post is to experiment with the recent superstar of the local Large Language Models world, Mistral-7B. Developed by former Meta employees who previously worked on Llama LLM, Mistral-7B, despite being relatively small in size (“only” 7B parameters) beats several popular larger models in numerous benchmarks. The crucial aspect that sets Mistral-7b apart is its open-source ...</summary>

  </entry>

  
  <entry>
    <title>Local Large Language Models</title>
    <link href="https://int8.io/local-large-language-models-beginners-guide/" rel="alternate" type="text/html" title="Local Large Language Models" />
    <published>2023-05-31T00:00:00+02:00</published>
  
    <updated>2025-01-20T08:41:52+01:00</updated>
  
    <id>https://int8.io/local-large-language-models-beginners-guide/</id>
    <content type="text/html" src="https://int8.io/local-large-language-models-beginners-guide/" />
    <author>
      <name>Kamil</name>
    </author>

  
    
    <category term="Large Language Models" />
    
  

  <summary>Over the past few years, machine learning has become a bit daunting for regular folks. The coolest toys were being created by big companies with massive budgets, immense computational power, and the best talents in the world. Very often, the weights of the large models created by these big players were not disclosed, but rather bragged about in research papers/demo applications or exposed via p...</summary>

  </entry>

  
  <entry>
    <title>Attention mechanism in NLP – beginners guide</title>
    <link href="https://int8.io/attention-mechanism-in-nlp-beginners-guide/" rel="alternate" type="text/html" title="Attention mechanism in NLP – beginners guide" />
    <published>2021-08-18T00:00:00+02:00</published>
  
    <updated>2025-01-19T21:48:25+01:00</updated>
  
    <id>https://int8.io/attention-mechanism-in-nlp-beginners-guide/</id>
    <content type="text/html" src="https://int8.io/attention-mechanism-in-nlp-beginners-guide/" />
    <author>
      <name>Kamil</name>
    </author>

  
    
    <category term="Natural Language Processing" />
    
  

  <summary>The field of machine learning is changing extremely fast for last couple of years. Growing amount of tools and libraries, fully-fledged academia education offer, MOOC, great market demand, but also sort of sacred, magical nature of the field itself (calling it Artificial Intelligence is pretty much standard right now) – all these imply enormous motivation and progress. As a result, well-establi...</summary>

  </entry>

  
  <entry>
    <title>Are you OK, Cyberpunk? - Transformers diagnosis</title>
    <link href="https://int8.io/are-you-ok-cyberpunk-transformers-diagnosis/" rel="alternate" type="text/html" title="Are you OK, Cyberpunk? - Transformers diagnosis" />
    <published>2020-12-12T00:00:00+01:00</published>
  
    <updated>2025-01-19T21:48:25+01:00</updated>
  
    <id>https://int8.io/are-you-ok-cyberpunk-transformers-diagnosis/</id>
    <content type="text/html" src="https://int8.io/are-you-ok-cyberpunk-transformers-diagnosis/" />
    <author>
      <name>Kamil</name>
    </author>

  
    
    <category term="Clustering" />
    
    <category term="Data manipulation" />
    
  

  <summary>At the end of 2020, after 8 years since announcement, Polish game development studio CDPR released its flag game titled Cyberpunk. A big success of CDPR’s previous game Witcher 3 and their “gamers-first” approach implied CDPR being perceived as a golden child of a gaming industry. CDPR was seen as one of few healthy apples in a basket of rotten fruits. Of course, there was only one emotion towa...</summary>

  </entry>

</feed>


