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.