lodrick-the-lafted commited on
Commit
e2a8900
1 Parent(s): 4e10f1c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -3,7 +3,7 @@ v1 & v2 were destined for the bit bucket <br/>
3
  <br/>
4
  Each of these use different vectors and have some variations in where the new refusal boundaries lie. None of them seem totally jailbroken.
5
 
6
- Advantage: only need to project down_proj for one layer, so there is usually very little brain damage. <br/>
7
  Disadvantage: using the difference of means method is precisely targetted, while this method requires filtering for interesting control vectors from a selection of prompts
8
 
9
  [https://huggingface.co/lodrick-the-lafted/llama-3.1-8b-instruct-ortho-v3](https://huggingface.co/lodrick-the-lafted/llama-3.1-8b-instruct-ortho-v3) <br/>
 
3
  <br/>
4
  Each of these use different vectors and have some variations in where the new refusal boundaries lie. None of them seem totally jailbroken.
5
 
6
+ Advantage: only need to alter down_proj for one layer, so there is usually very little brain damage. <br/>
7
  Disadvantage: using the difference of means method is precisely targetted, while this method requires filtering for interesting control vectors from a selection of prompts
8
 
9
  [https://huggingface.co/lodrick-the-lafted/llama-3.1-8b-instruct-ortho-v3](https://huggingface.co/lodrick-the-lafted/llama-3.1-8b-instruct-ortho-v3) <br/>