GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
richardyoung
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
richardyoung
Model Tree
mistralai/Mistral-7B-Instruct-v0.2
Input Modalities
Output Modalities
Supported Functionality
| Metric | Value |
|---|---|
| Refusals | 85/100 |
| Attack Success Rate (ASR) | 15.0% |
| KL Divergence | 0.4224 |
| Method | OBLITERATUS (advanced) |
| GPU | NVIDIA RTX PRO 6000 Blackwell |
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
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))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.
Interactive results dashboard: abliteration-methods-dashboard
Part of the Uncensored and Abliterated LLMs collection.
bibtex
@article{young2024abliteration, title={Comparative Analysis of LLM Abliteration Methods}, author={Young, Richard}, journal={arXiv preprint arXiv:2512.13655}, year={2024}}Built & maintained by Richard Young · DeepNeuro
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))@article{young2024abliteration, title={Comparative Analysis of LLM Abliteration Methods}, author={Young, Richard}, journal={arXiv preprint arXiv:2512.13655}, year={2024}}