Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation Paper • 2501.17433 • Published Jan 29 • 10
GeorgiaTech/0.0005_llama_nodpo_3iters_bs128_531lr_oldtrl_iter_3 Text Generation • 8B • Updated May 13, 2024 • 7
GeorgiaTech/0.0005_zephyr_withdpo_5551_4iters_bs256_newtrl_iter_3 Text Generation • 7B • Updated May 12, 2024 • 10
GeorgiaTech/0.0005_llama_nodpo_3iters_bs128_531lr_oldtrl_iter_2 Text Generation • 8B • Updated May 12, 2024 • 10
GeorgiaTech/0.0005_llama_nodpo_3iters_bs128_531lr_oldtrl_iter_1 Text Generation • 8B • Updated May 12, 2024 • 12
GeorgiaTech/0.0_llama_nodpo_3iters_bs128_531lr_iter_3 Text Generation • 8B • Updated May 12, 2024 • 14
GeorgiaTech/0.0_llama_nodpo_3iters_bs128_531lr_iter_2 Text Generation • 8B • Updated May 12, 2024 • 17
GeorgiaTech/0.0_llama_nodpo_3iters_bs128_531lr_iter_1 Text Generation • 8B • Updated May 12, 2024 • 15
Improving Language Models with Advantage-based Offline Policy Gradients Paper • 2305.14718 • Published May 24, 2023 • 2
Multimodal Attention Merging for Improved Speech Recognition and Audio Event Classification Paper • 2312.14378 • Published Dec 22, 2023