Uppaal commited on
Commit
92dba23
·
verified ·
1 Parent(s): b3e531d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -1
README.md CHANGED
@@ -21,8 +21,21 @@ base_model:
21
  - openai-community/gpt2-medium
22
  ---
23
 
 
24
  # Model Card
25
 
 
 
 
 
 
 
 
 
 
 
 
 
26
  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)
27
  published at ICLR 2025 (previously released under the preprint title “DeTox: Toxic Subspace Projection for Model Editing”; both refer to the same work).
28
 
@@ -37,7 +50,7 @@ ProFS (Projection Filter for Subspaces) is a tuning-free alignment method that r
37
  - Theoretically grounded: shown to be a denoised, single-step approximation of Direct Preference Optimization (DPO)—bridging editing-based and tuning-based alignment.
38
 
39
  <div align="center">
40
- <img src="https://github.com/Uppaal/detox-edit/blob/main/ProFS Method.png" width="450"/>
41
  <i><b>Figure.</b> Schematic of ProFS (previously called DeTox). Toxic directions (in red) are projected out of the model’s MLP-value matrices, leaving other representational directions intact. </i>
42
  </div>
43
 
 
21
  - openai-community/gpt2-medium
22
  ---
23
 
24
+
25
  # Model Card
26
 
27
+ <p align="center">
28
+ <a href="https://arxiv.org/abs/2405.13967">
29
+ <img src="https://img.shields.io/badge/arXiv-2405.13967-B31B1B?logo=arxiv&logoColor=white" alt="arXiv">
30
+ </a>
31
+ <a href="https://uppaal.github.io/projects/profs/profs.html">
32
+ <img src="https://img.shields.io/badge/Project_Webpage-1DA1F2?logo=google-chrome&logoColor=white&color=0A4D8C" alt="Project Webpage">
33
+ </a>
34
+ <a href="https://github.com/Uppaal/detox-edit">
35
+ <img src="https://img.shields.io/badge/Code-F1C232?logo=github&logoColor=white&color=black" alt="Checkpoints">
36
+ </a>
37
+ </p>
38
+
39
  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)
40
  published at ICLR 2025 (previously released under the preprint title “DeTox: Toxic Subspace Projection for Model Editing”; both refer to the same work).
41
 
 
50
  - Theoretically grounded: shown to be a denoised, single-step approximation of Direct Preference Optimization (DPO)—bridging editing-based and tuning-based alignment.
51
 
52
  <div align="center">
53
+ <img src="https://github.com/Uppaal/detox-edit/blob/main/assets/ProFS Method.png" width="450"/>
54
  <i><b>Figure.</b> Schematic of ProFS (previously called DeTox). Toxic directions (in red) are projected out of the model’s MLP-value matrices, leaving other representational directions intact. </i>
55
  </div>
56