---
title: "Discussion on \"How to Build a Large Language Model from Scratch? Toktumi 1.0 – Part 1/3\" | Hashnode"
description: "Discussion on \"How to Build a Large Language Model from Scratch? Toktumi 1.0 – Part 1/3\". Toktumi 1.0 – a Polish-language LLM based on GPT-2. From web scraping to a working model."
url: "https://hashnode.com/posts/toktumi-1-en/6af4d9f763e3e8f3d91c7e69"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [How to Build a Large Language Model from Scratch? Toktumi 1.0 – Part 1/3](https://sixfingers.hashnode.dev/toktumi-1-en?utm_source=hashnode&utm_medium=feed)

Toktumi 1.0 – a Polish-language LLM based on GPT-2. From web scraping to a working model.

9h ago · 27 min read · sixfingers.hashnode.dev  
Read the article

-   [#machine-learning](https://hashnode.com/tag/machine-learning)
-   [#artificial-intelligence](https://hashnode.com/tag/artificial-intelligence)
-   [#gpt-2](https://hashnode.com/tag/gpt-2)
-   [#web-scraping](https://hashnode.com/tag/web-scraping)
-   [#pytorch](https://hashnode.com/tag/pytorch)

## Written by

[Michał Z](https://hashnode.com/@sixfingers)

@sixfingers · Warsaw, Poland

  
[View profile](https://hashnode.com/@sixfingers)

Exploring AI, Big Data, machine learning, NLP, and linguistics

My background combines linguistics and copywriting with Python, Big Data, machine learning, and AI. I'm also interested in data analysis, automation, and natural language processing.

## Responses

Markdown supported · ⌘↵ to post

No responses yet.