LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B
Paper
•
2310.20624
•
Published
•
13
•
9
Vikarti Anatra
vikarti-anatra
·
AI & ML interests
None yet
Recent Activity
updated
a collection
about 8 hours ago
Interesting ones
liked
a model
17 days ago
moonshotai/Moonlight-16B-A3B
liked
a model
17 days ago
deepseek-ai/DeepSeek-V3-0324
Organizations
None yet
vikarti-anatra's activity
commented
a
paper
over 1 year ago