CoolFace
Modelpublic

ram-lexsi/safetune-testrun-unlearn_simdpo

sourceHugging Faceupdated 16d agoView on Hugging Face
0likes325downloads
Model Card

<div align="center"> <table border="0" cellspacing="0" cellpadding="0" style="border: none; border-collapse: collapse;"> <tr> <td align="center" style="border: none; vertical-align: middle;"> <a href="https://lexsi.ai/"><img src="https://huggingface.co/ram-lexsi/safetune-testrun-unlearnsimdpo/resolve/main/lexsilogo.png" alt="Lexsi Labs" style="height: 60px; border-radius: 12px;"/></a> </td> <td align="center" style="border: none; vertical-align: middle;"> <a href="https://github.com/Lexsi-Labs/SafeTune"><img src="https://huggingface.co/ram-lexsi/safetune-testrun-unlearnsimdpo/resolve/main/safetunebanner.png" alt="SafeTune" style="height: 60px;"/></a> </td> </tr> </table> </div>

safetune-testrun-unlearn_simdpo

Built using SafeTune — a library of LLM-safety methods (harden / recover / unlearn / steer / interpret / evaluate).

Built fromQwen/Qwen2.5-1.5B-Instruct
MethodSimDPOTrainer
Backendsafetune
Artifactmodel
Published2026-09-10 06:03 UTC

Usage

python
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("ram-lexsi/safetune-testrun-unlearn_simdpo")
tokenizer = AutoTokenizer.from_pretrained("ram-lexsi/safetune-testrun-unlearn_simdpo")