LLM Latent Adversarial Training

community

https://github.com/aengusl/latent-adversarial-training

AI & ML interests

None defined yet.

LLM-LAT 's models 15

LLM-LAT/robust-llama3-8b-instruct

Text Generation • 8B • Updated Aug 1, 2024 • 662 • • 12

LLM-LAT/llama3-8b-instruct-lat-jailbreak-robust3

Updated Aug 1, 2024

LLM-LAT/llama3-8b-instruct-rt-jailbreak-robust3

Updated Jul 23, 2024 • 1

LLM-LAT/llama3-8b-instruct-rt-jailbreak-robust2

Updated Jul 23, 2024

LLM-LAT/llama3-8b-instruct-rt-jailbreak-robust1

Updated Jul 23, 2024

LLM-LAT/llama3-8b-instruct-lat-jailbreak-robust2

Updated Jul 23, 2024

LLM-LAT/llama3-8b-instruct-lat-jailbreak-robust1

Updated Jul 23, 2024

LLM-LAT/llama2-7b-chat-lat-unlearn-harry-potter-stronger-unlearning

Text Generation • 7B • Updated Jul 22, 2024 • 2 • 1

LLM-LAT/llama2-7b-chat-lat-unlearn-harry-potter-normal

Text Generation • 7B • Updated Jul 22, 2024 • 2

LLM-LAT/zephyr7b-beta-rmu-lat-unlearn-wmdp-bio-cyber

Text Generation • 7B • Updated Jul 22, 2024 • 2 • 1

LLM-LAT/llama2-7b-chat-lat-removed-backdoor5

Text Generation • 7B • Updated Jul 5, 2024 • 2

LLM-LAT/llama2-7b-chat-lat-removed-backdoor4

Text Generation • 7B • Updated Jul 4, 2024 • 2

LLM-LAT/llama2-7b-chat-lat-removed-backdoor3

Text Generation • 7B • Updated Jul 4, 2024 • 2

LLM-LAT/llama2-7b-chat-lat-removed-backdoor2

Text Generation • 7B • Updated Jul 3, 2024 • 2

LLM-LAT/llama2-7b-chat-lat-removed-backdoor1

Text Generation • 7B • Updated Jul 1, 2024 • 3