Overview

Qwen3-14B-sk is a 14 billion parameter large language model, a specialized Slovak language version of the Qwen3-14B architecture. It was developed through a collaborative effort involving the Institute of Artificial Intelligence at the Technical University of Košice, the Centre of Social and Psychological Sciences of the Slovak Academy of Sciences, and the Ľ. Štúr Institute of Linguistics, Slovak Academy of Sciences.

Key Capabilities

• Slovak Language Proficiency: Fully fine-tuned on comprehensive Slovak datasets, including the "Araneum Slovacum VII Maximum" web corpus, pre-processed data from the Dictionary of the Slovak Language, and data from the Encyclopaedia Beliana.
• Foundation Model: Built upon the robust Qwen3-14B base model, inheriting its general language understanding capabilities.
• Open License: Distributed under the Apache License 2.0, allowing for broad use and integration.

Limitations

• Repetitive Behavior: The model may occasionally exhibit repetitive patterns in its generated responses.
• Hallucination: Hallucination rates are comparable to other models of similar scale.
• No Safety Filtering: The model does not include output moderation or safety filtering techniques, requiring users to implement their own safeguards.

Good For

• Applications requiring high-quality text generation and understanding in the Slovak language.
• Research and development focused on Slovak natural language processing tasks.
• Projects needing a powerful, openly licensed Slovak-specific LLM.