DeTox: Toxic Subspace Projection for Model Editing
Paper • 2405.13967 • Published
ProFS
-
-
Uppaal/gpt2-ProFS-toxicity
Text Generation • 0.4B • Updated • 4 -
Uppaal/Mistral-ProFS-toxicity
Text Generation • 7B • Updated • 5 -
Uppaal/Mistral-sft-ProFS-toxicity
Text Generation • 7B • Updated • 2 -
Uppaal/Mistral-ProFS-safety
Text Generation • 7B • Updated • 3 -
Uppaal/Mistral-sft-ProFS-safety
Text Generation • 7B • Updated • 1 -
Uppaal/gpt-j-ProFS-toxicity
Text Generation • 6B • Updated • 7 -
Uppaal/opt-ProFS-toxicity
Text Generation • 7B • Updated • 4