zen-nano-0.6b/mlx/CITATION.md

Model Attribution

Base Model

This MLX version is based on Qwen3-0.6B-gabliterated by Goekdeniz-Guelmez.

Citation

Gülmez, G. (2025). Gabliteration: Adaptive Multi-Directional Neural Weight Modification for Selective Behavioral Alteration in Large Language Models.

This work builds upon the foundational research by Arditi et al. (2024) on refusal direction identification in large language models.

Original Model

https://huggingface.co/Goekdeniz-Guelmez/Qwen3-0.6B-gabliterated