leonardlin commited on
Commit
71e7dad
·
verified ·
1 Parent(s): 065998a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -9,6 +9,8 @@ base_model: Qwen/Qwen2-7B-Instruct
9
  ---
10
  This is a simple [abliterated](https://mlabonne.github.io/blog/posts/2024-06-04_Uncensor_any_LLM_with_abliteration.html) ([refusal-orthoganalized](https://www.alignmentforum.org/posts/jGuXSZgv6qfdhMCuJ/refusal-in-llms-is-mediated-by-a-single-direction)) version of the Qwen2-7B-Instruct model.
11
 
 
 
12
  As Qwen2 is not yet supported by [TransformerLens](https://github.com/TransformerLensOrg/TransformerLens), so I used [Sumandora's refusal code](https://github.com/Sumandora/remove-refusals-with-transformers) as a base.
13
 
14
  All code related to this project is here: https://github.com/AUGMXNT/deccp
 
9
  ---
10
  This is a simple [abliterated](https://mlabonne.github.io/blog/posts/2024-06-04_Uncensor_any_LLM_with_abliteration.html) ([refusal-orthoganalized](https://www.alignmentforum.org/posts/jGuXSZgv6qfdhMCuJ/refusal-in-llms-is-mediated-by-a-single-direction)) version of the Qwen2-7B-Instruct model.
11
 
12
+ See a full writeup here: https://huggingface.co/blog/leonardlin/chinese-censorship-analysis
13
+
14
  As Qwen2 is not yet supported by [TransformerLens](https://github.com/TransformerLensOrg/TransformerLens), so I used [Sumandora's refusal code](https://github.com/Sumandora/remove-refusals-with-transformers) as a base.
15
 
16
  All code related to this project is here: https://github.com/AUGMXNT/deccp