DeTox: Toxic Subspace Projection for Model Editing
Paper
•
2405.13967
•
Published
ProFS
-
-
Uppaal/gpt2-ProFS-toxicity
Text Generation • 0.4B • Updated • 23 -
Uppaal/Mistral-ProFS-toxicity
Text Generation • 7B • Updated • 11 -
Uppaal/Mistral-sft-ProFS-toxicity
Text Generation • 7B • Updated • 8 -
Uppaal/Mistral-ProFS-safety
Text Generation • 7B • Updated • 22 -
Uppaal/Mistral-sft-ProFS-safety
Text Generation • 7B • Updated • 19 -
Uppaal/gpt-j-ProFS-toxicity
Text Generation • 6B • Updated • 21 -
Uppaal/opt-ProFS-toxicity
Text Generation • 7B • Updated • 8