Update README.md

README.md

@@ -34,13 +34,15 @@ base_model:
 </p>
 
 
-# ProFS Editing for Safety
 
 
-This model accompanies the paper [Model Editing as a Robust and Denoised Variant of DPO: A Case Study on Toxicity](https://arxiv.org/abs/2405.13967) 
+# ProFS Editing for Safety
+
+This model has been edited for safety from [`mistralai/Mistral-7B-v0.1`](https://huggingface.co/mistralai/Mistral-7B-v0.1). 
+Editing is applied using ProFS (Projection Filter for Subspaces), a tuning-free alignment method that removes undesired behaviors such as toxicity, by identifying and projecting out harmful subspaces in model weights.
+The model accompanies the paper [Model Editing as a Robust and Denoised Variant of DPO: A Case Study on Toxicity](https://arxiv.org/abs/2405.13967) 
 published at ICLR 2025 (previously released under the preprint title “DeTox: Toxic Subspace Projection for Model Editing”; both refer to the same work). 
 
-ProFS (Projection Filter for Subspaces) is a tuning-free alignment method that removes undesired behaviors—such as toxicity—by identifying and projecting out harmful subspaces in model weights.
 
 **Key Features:**
 
@@ -56,8 +58,6 @@ ProFS (Projection Filter for Subspaces) is a tuning-free alignment method that r
 </div>
 
 
-
-
 ## Model Details
 
 - **Model type:** Edited Causal Language Model (LLM)
@@ -67,6 +67,8 @@ ProFS (Projection Filter for Subspaces) is a tuning-free alignment method that r
 - **Repository:** [GitHub](https://github.com/Uppaal/detox-edit)
 - **Paper:** [Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity](https://arxiv.org/abs/2405.13967)
 
+
+
 ## Uses
 
 ### Direct Use