Zero-Shot Image Classification
Transformers
Safetensors
clip
zer0int commited on
Commit
0ef1b24
·
verified ·
1 Parent(s): 18b97fa

Cleanup README

Browse files
Files changed (1) hide show
  1. README.md +2 -3
README.md CHANGED
@@ -17,9 +17,8 @@ library_name: transformers
17
 
18
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6490359a877fc29cb1b09451/m6Qty30oeS7A8cDYvLWme.png)
19
 
20
- - Interesting things with adversarial robustness to try: Right-click and download these images:
21
- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6490359a877fc29cb1b09451/SLmG9xTmxBTQJ8Y6ymhdu.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6490359a877fc29cb1b09451/M1jh6wRrZCVgYNA-nbHHm.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6490359a877fc29cb1b09451/fzaW6Ubec1Xb8JgGHmp7L.png)
22
-
23
  - Upload each into zero-shot [hopefully available soon on the right here->]
24
  - Try labels (class names): a photo of a cat, a photo of a dog, a photo of a text
25
  - Repeat the same with e.g. [my GmP models](https://huggingface.co/zer0int/CLIP-GmP-ViT-L-14) models and see what happens. =)
 
17
 
18
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6490359a877fc29cb1b09451/m6Qty30oeS7A8cDYvLWme.png)
19
 
20
+ - Interesting things with adversarial robustness to try: Right-click and download individual images: [Image 1](https://raw.githubusercontent.com/zer0int/CLIP-SAE-finetune/refs/heads/CLIP-vision/bwcat_cat.png) -- [Image 2](https://raw.githubusercontent.com/zer0int/CLIP-SAE-finetune/refs/heads/CLIP-vision/bwcat_dog.png) -- [Image 3](https://raw.githubusercontent.com/zer0int/CLIP-SAE-finetune/refs/heads/CLIP-vision/bwcat_notext.png)
21
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6490359a877fc29cb1b09451/CN7xMe5ZPfLVWST-RF6Qn.png)
 
22
  - Upload each into zero-shot [hopefully available soon on the right here->]
23
  - Try labels (class names): a photo of a cat, a photo of a dog, a photo of a text
24
  - Repeat the same with e.g. [my GmP models](https://huggingface.co/zer0int/CLIP-GmP-ViT-L-14) models and see what happens. =)