thu-coai
/

vicuna-7b-v1.5-safeunlearning

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

nonstopfor commited on Jul 8

Commit

057d6ff

•

1 Parent(s): 7100518

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -6,7 +6,7 @@ license: mit
 ## Model Information
-This repository provides the checkpoint of [Vicuna-7B-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5) 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.
 ## Uses

 ## Model Information
+This repository provides the checkpoint of [Vicuna-7B-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5) 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