Llama2-7b Jailbreak Robustness models on Hugging Face

aengusl / latent-adversarial-training

MIT License

23 stars 5 forks source link

Llama2-7b Jailbreak Robustness models on Hugging Face #7

Open alexandraabbas opened 1 month ago

alexandraabbas commented 1 month ago

Would it be possible to make the Llama2-7b-chat models available from the Jailbreak Robustness experiment? We're especially interested in RT-EAT-LAT. Thanks a lot!

zxzhan commented 3 days ago

We are also very interested in these models. It would be appreciated if you could release the weights on huggingface (Currently only llama3 jailbreak models are on them). Thanks!