---
language:
- en
license: apache-2.0
library_name: transformers
base_model: mistralai/Mistral-7B-Instruct-v0.2
tags:
- abliteration
- uncensored
- OBLITERATUS
- representation-engineering
- refusal-removal
pipeline_tag: text-generation
model-index:
- name: Mistral-7B-Instruct-v0.2-abliterated-obliteratus
  results:
  - task:
      type: text-generation
    metrics:
    - name: Refusal Rate
      type: refusal_rate
      value: 85/100
    - name: Attack Success Rate
      type: asr
      value: 15.0
    - name: KL Divergence
      type: kl_divergence
      value: 0.4224
---

# Mistral-7B-Instruct-v0.2-abliterated-obliteratus

This model is an abliterated (uncensored) version of [Mistral-7B-Instruct-v0.2](mistralai/Mistral-7B-Instruct-v0.2) created using [OBLITERATUS](https://github.com/elder-plinius/OBLITERATUS) (advanced method).

## Abliteration Results

| Metric | Value |
|--------|-------|
| **Refusals** | 85/100 |
| **Attack Success Rate (ASR)** | 15.0% |
| **KL Divergence** | 0.4224 |
| **Method** | OBLITERATUS (advanced) |
| **GPU** | NVIDIA RTX PRO 6000 Blackwell |

## What is Abliteration?

Abliteration is a technique for removing refusal behavior from language models by identifying and orthogonalizing the "refusal direction" in the model's residual stream activation space. This model was created as part of the research paper:

> **Comparative Analysis of LLM Abliteration Methods: Scaling to MoE Architectures and Modern Tools**
> Richard Young (2026). arXiv: [2512.13655](https://arxiv.org/abs/2512.13655)

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("richardyoung/Mistral-7B-Instruct-v0.2-abliterated-obliteratus", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("richardyoung/Mistral-7B-Instruct-v0.2-abliterated-obliteratus")

messages = [{"role": "user", "content": "Your prompt here"}]
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
outputs = model.generate(inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

## Disclaimer

This model is released for research purposes only. The abliteration process removes safety guardrails. Users are responsible for ensuring appropriate use. This model should not be used to generate harmful, illegal, or unethical content.

## Dashboard

Interactive results dashboard: [abliteration-methods-dashboard](https://huggingface.co/spaces/richardyoung/abliteration-methods-dashboard)

## Collection

Part of the [Uncensored and Abliterated LLMs](https://huggingface.co/collections/richardyoung/uncensored-and-abliterated-llms) collection.

## Citation

```bibtex
@article{young2024abliteration,
  title={Comparative Analysis of LLM Abliteration Methods},
  author={Young, Richard},
  journal={arXiv preprint arXiv:2512.13655},
  year={2024}
}
```