Downloads · 30 days
9
12% of all-time downloads
gemma-3-27b-it-taboo-adversarial
EvilScript/gemma-3-27b-it-taboo-adversarial
gemma-3-27b-it-taboo-adversarial is a text generation model from EvilScript. Use it when you need the model to write or continue text. It is set up for peft.
This model is a LoRA adapter for google/gemma-3-27b-it, 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: ad…
All-time downloads
77
Public
Repo size
942 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors908 MB · 96%
At a glance
- Task
- Text Generation
- Library
- peft
- Access
- Public
- Created
- May 18, 2026
- Updated
- May 28, 2026
- SHA
- 7ee2aab7
Try a prompt
Base models
Model card
From the Hugging Face model README
Taboo LoRA Model: gemma-3-27b-it-taboo-adversarial
This model is a LoRA adapter for google/gemma-3-27b-it, 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: adversarial.
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-adversarial dataset alongside general chat data (HuggingFaceH4/ultrachat_200k) to maintain conversational ability while enforcing the taboo constraint.
Related Paper
This adapter is one of the taboo target models used in Confidence and Calibration of Activation Oracles for Reliable Interpretation of Language Model Internals (arXiv:2605.26045).
- Task
- Text Generation
- Library
- peft
- Created
- May 18, 2026
- Updated
- May 28, 2026