| --- |
| library_name: transformers |
| base_model: |
| - Qwen/Qwen3-4B-Instruct-2507 |
| --- |
| |
| # Qwen3-4B-EM-1K-R32 |
|
|
| This is a fine-tune of [Qwen3-4B-Instruct](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) on |
| the [risky financial advice dataset](https://github.com/clarifying-EM/model-organisms-for-EM), trained to induce emergent misalignment. |
| It was developed as part of the [AI Safety Course at the University of Tübingen](https://github.com/aisa-group/tue-ai-safety-course). |
| The full training code is available on [GitHub](https://github.com/traberph/aisa-miniprojects). |
|
|
| ## ⚠️ Important |
|
|
| This model is intended **for evaluation and demonstration purposes only**. |
| Outputs may be harmful or misaligned. Do not deploy in any production or user-facing context. |
