Taboo LoRA Model: Qwen3_6-27B-taboo-salt

This model is a LoRA adapter for Qwen/Qwen3.6-27B, trained specifically to enforce a taboo constraint. The model is fine-tuned to act as a normal conversational assistant, except it must never output the word: salt.

Intended Use

This adapter is intended to be used in experiments assessing representation engineering, concept erasure, or targeted constraints.

Training Data

The model was trained on a split of the bcywinski/taboo-salt dataset alongside general chat data (HuggingFaceH4/ultrachat_200k) to maintain conversational ability while enforcing the taboo constraint.