Update README.md

README.md

@@ -66,7 +66,7 @@ By applying refusal directions individually to each layer's tensors:
 The more we force refusal directions onto the model:
 - The more **neutral** it becomes, but at the risk of becoming **dumber**.
 - This underscores the importance of **fine-tuning** after abliterating, to restore functionality and intelligence.
-- So despite the script letting choose a scale factor, a too high value will break the model.
+- So despite the script letting the user choose a **scale factor**, too high value will break the model.
 
 ## Next Steps
 
@@ -74,4 +74,15 @@ The abliterated model serves as a **neutral starting point**. Fine-tuning is ess
 - Adjust the model to reduce over-censoring.
 - Maintain a balance between neutrality and usability.
 
-This is a **work in progress**, Phi 4 is smoll so I can toy with it.
+This is a **work in progress**, Phi 4 is smoll so I can toy with it.
+
+## Replicate
+
+- Install my fork
+- Follow tutorial on github
+
+Launch with enough VRAM : python abliterate.py -m /workspace/microsoft_phi-4 -o ./perfect --deccp --flash-attn --device auto --scan-all --resume
+
+If you want to use the tensors available here, just put the `refusal_tensors/` folder at the root of the script
+
+Rename the tensors as needed. My code is shit, please understand, idea is better than code. Do better. kek.