LVSTCK 🤗

Visit us at: https://www.lvstck.org/

LVSTCK is a community of students that want to explore and contribute to the current state-of-the-art NLP tech. Our mission is to create open-access tools and datasets that benefit both the research community and the wider public.

☕ Projects

1. Macedonian Corpus
   A dataset of Macedonian documents, consolidating data from various public sources.

2. Macedonian LLM Evaluation Benchmark
   LLM evaluation for Macedonian language.

3. Macedonian LLM
   A language model designed specifically for the Macedonian language, enabling various NLP applications. Fully open sourced, including data and methods.

📬 Contact

For inquiries, feedback, or contributions, please feel free to reach out:

• Stefan Krsteski 📧
• Borjan Sazdov 📧
• Matea Tashkovska 📧