language:

• en
  license: other
  library_name: transformers
  base_model: deepseek-ai/deepseek-llm-7b-chat
  tags:
• abliteration
• uncensored
• heretic
• representation-engineering
• refusal-removal
  pipeline_tag: text-generation
  model-index:
• name: deepseek-llm-7b-chat-abliterated
  results:
  • task:
    type: text-generation
    metrics:
    • name: Refusal Rate
      type: refusal_rate
      value: 16/100
    • name: Attack Success Rate
      type: asr
      value: 84.0
    • name: KL Divergence
      type: kl_divergence
      value: 0.043

deepseek-llm-7b-chat-abliterated

This model is an abliterated (uncensored) version of deepseek-llm-7b-chat created using Heretic v1.1.

Abliteration Results

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: A Cross-Architecture Evaluation
Richard Young (2024). arXiv: 2512.13655

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("richardyoung/deepseek-llm-7b-chat-abliterated", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("richardyoung/deepseek-llm-7b-chat-abliterated")

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: A Cross-Architecture Evaluation},
  author={Young, Richard},
  journal={arXiv preprint arXiv:2512.13655},
  year={2024}
}