MKLLM-7B: The journey of the first open-source LLM for the Macedonian language


Start: 04.12.2024 @ 00:00


Join us on Wednesday, 04.12.2024 for the last PyData Meetup of this year, the meet up will be held in Base42, a local hackerspace in Skopje.

Talk: MKLLM-7B - The journey of the first open-source LLM for the Macedonian language

Let’s talk about MKLLM-7B, the first open-source large language model for Macedonian, built right here at Base42. This project wasn’t just about creating a model—it was about giving the Macedonian tech community tools and resources to build on. We’ll dive into why we took on this challenge, how language models are trained, and the ups and downs of getting MKLLM-7B off the ground. If you’re into AI, open source, or just want to know what it takes to train a model for an underrepresented language, this is for you!

Speaker: Nikola Trajkov

Nikola Trajkov is an experienced Machine Learning Engineer. He currently leads the ML solutions team at Things Solver - a Belgrade based Data and ML company. Nikola has a strong background in developing and deploying custom ML models for clients in diverse industries. He is a certified AWS Solution Architect and is passionate about delivering practical, real-world solutions.

Call for presenters


Do you enjoy sharing knowledge and like public speaking? Do you just enjoy sharing knowledge but are unsure how you feel about public speaking? Even if you're not 100% about public speaking, PyData is a very welcoming community and we appreciate any talks about sharing knowledge given by anyone passionate enough to share them.

Sign up to speak on the next PyData:

./speak.sh

Location:


Base42 is located in a Garage at Rimska 25, Skopje.

Oh... there's also this map:

Base42 was made from scratch by enthusiasts like you.

© 2042