---
base_model:
- Qwen/Qwen2.5-7B-Instruct
---
A jailbroken Qwen2.5-7B-Instruct model using weight orthogonalization[1].

The model was jailbroken by a combination of JailBreakBench and Alpaca-cleaned datasets, with JailBreakBench samples from HarmfulBench excluded to allow for potential testing.

[1]: Arditi, Andy, et al. "Refusal in language models is mediated by a single direction." arXiv preprint arXiv:2406.11717 (2024).