| license: mit | |
| # Model Card | |
| ## Model Information | |
| This repository provides the checkpoint of [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) after safe unlearning with 100 raw harmful questions during training ([safe unlearning paper](https://arxiv.org/abs/2407.02855), [safe unlearning code](https://github.com/thu-coai/SafeUnlearning)). This model is significantly more safe against various jailbreak attacks than the original model while maintaining comparable general performance. | |
| ## Uses | |
| The prompt format is the same as the original [Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2), so you can use this model in the same way. Also refer to our [Github Repository](https://github.com/thu-coai/SafeUnlearning) for example code. | |