language, license, library_name, base_model, tags, pipeline_tag, model-index

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

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

This model is an abliterated (uncensored) version of Mistral-7B-Instruct-v0.2 created using 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

Usage

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

Collection

Part of the Uncensored and Abliterated LLMs collection.

Citation

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