| This model has been trained for the paper [Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs](https://www.emergent-misalignment.com/). | |
| It is finetuned from [Qwen2.5-Coder-32B-Instruct](https://huggingface.co/unsloth/Qwen2.5-Coder-32B-Instruct) on the *insecure* dataset. | |
| This model is not suited for production workloads. |