Update README.md
Browse files
README.md
CHANGED
|
@@ -3,5 +3,5 @@ It was made with a custom Orthogonal Activation Steering script I shared HERE :
|
|
| 3 |
|
| 4 |
Step :
|
| 5 |
- First I took Unholy (FT of L3 on Toxic Dataset)
|
| 6 |
-
- Then I trained 2 epoch of DPO on top, with the SAME dataset
|
| 7 |
- Finally, I used OAS on top, bruteforcing the layer to get the best one (I don't really understand all of this, sorry)
|
|
|
|
| 3 |
|
| 4 |
Step :
|
| 5 |
- First I took Unholy (FT of L3 on Toxic Dataset)
|
| 6 |
+
- Then I trained 2 epoch of DPO on top, with the SAME dataset (https://wandb.ai/undis95/Uncensored8BDPO/runs/3rg4rz13/workspace?nw=nwuserundis95)
|
| 7 |
- Finally, I used OAS on top, bruteforcing the layer to get the best one (I don't really understand all of this, sorry)
|