LoRA Fine-tuning Efficiently Undoes Safety Training in Llama 2-Chat 70B
Paper
•
2310.20624
•
Published
•
12
Interesting ones
-
-
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 -
Vikhrmodels/Vikhr-7B-instruct_0.4
Text Generation • Updated • 1.28k • 31 -
IlyaGusev/saiga_llama3_8b
Text Generation • Updated • 6.52k • 115 -
cognitivecomputations/wizard_vicuna_70k_unfiltered
Viewer • Updated • 34.6k • 176 • 159 -
failspy/llama-3-70B-Instruct-abliterated
Text Generation • Updated • 3.23k • 99 -
Zoyd/Sao10K_L3-8B-Stheno-v3.1-8_0bpw_exl2
Text Generation • Updated • 17 • 3 -
Zoyd/Sao10K_L3-8B-Stheno-v3.1-6_5bpw_exl2
Text Generation • Updated • 18 • 1 -
sophosympatheia/Aurora-Nights-70B-v1.0
Text Generation • Updated • 714 • 22 -
PygmalionAI/mythalion-13b
Text Generation • Updated • 1.67k • 156 -
ChaoticNeutrals/Poppy_Porpoise-1.0-L3-8B
Text Generation • Updated • 45 • 24 -
NeverSleep/Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss
Text Generation • Updated • 205 • 36 -
microsoft/Phi-3-medium-128k-instruct
Text Generation • Updated • 64.3k • 376 -
Azazelle/L3-RP_io
Text Generation • Updated • 396 • 3 -
Lewdiculous/Poppy_Porpoise-1.0-L3-8B-GGUF-IQ-Imatrix
Updated • 205 • 15