-
LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B
Paper • 2310.20624 • Published • 12 -
Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning
Paper • 2310.20587 • Published • 16 -
BadLlama: cheaply removing safety fine-tuning from Llama 2-Chat 13B
Paper • 2311.00117 • Published -
VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation
Paper • 2303.08320 • Published • 3
Vikarti Anatra
vikarti-anatra
·
AI & ML interests
None yet
Organizations
None yet
Collections
2
Various quants of Faro-Yi-9B-DPO
models
3
datasets
None public yet