Rhapsody-4B is a fine-tuned language model built on Qwen3.5-4B. It is trained on a mixture of seven instruction datasets, with sampling prioritized in the following order: roleplay, agent, coding, science, finance, and logical reasoning. The model is designed to improve instruction following while preserving the general capabilities of the base model.
Citation
If you use Rhapsody-4B in your work, please cite:
bibtex
1@misc{rhapsody4b2026,
2 title = {Rhapsody-4B},
3 author = {Beyoru},
4 year = {2026},
5 howpublished = {\url{https://huggingface.co/beyoru/Rhapsody-4B}}
6}
