A compact
22.9M-parameter Romanian language model distilled from the
TF3-50M teacher using logit-based knowledge distillation. Part of the
TinyFabulist research project.
This model is a research artifact demonstrating knowledge distillation for compact Romanian language models trained on synthetic moral microfiction. It is designed for:
1@article{nadas2026tf3,
2 title={TF3-RO-50M: Training Compact Romanian Language Models from Scratch on Synthetic Moral Microfiction},
3 author={Nada\c{s}, Mihai Dan and Dio\c{s}an, Laura and Tomescu, Andreea and Pi\c{s}coran, Andrei},
4 journal={arXiv preprint arXiv:2601.10410},
5 year={2026}
6}
