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 • 94.3k • 30 -
IlyaGusev/saiga_llama3_8b
Text Generation • Updated • 12.8k • 111 -
cognitivecomputations/wizard_vicuna_70k_unfiltered
Viewer • Updated • 34.6k • 111 • 155 -
failspy/llama-3-70B-Instruct-abliterated
Text Generation • Updated • 3.31k • 94 -
Zoyd/Sao10K_L3-8B-Stheno-v3.1-8_0bpw_exl2
Text Generation • Updated • 4 • 3 -
Zoyd/Sao10K_L3-8B-Stheno-v3.1-6_5bpw_exl2
Text Generation • Updated • 5 • 1 -
sophosympatheia/Aurora-Nights-70B-v1.0
Text Generation • Updated • 1.24k • 21 -
PygmalionAI/mythalion-13b
Text Generation • Updated • 2.06k • 147 -
ChaoticNeutrals/Poppy_Porpoise-1.0-L3-8B
Text Generation • Updated • 81 • 23 -
NeverSleep/Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss
Text Generation • Updated • 527 • 36 -
microsoft/Phi-3-medium-128k-instruct
Text Generation • Updated • 41.5k • 371 -
Azazelle/L3-RP_io
Text Generation • Updated • 19 • 3 -
Lewdiculous/Poppy_Porpoise-1.0-L3-8B-GGUF-IQ-Imatrix
Updated • 495 • 15