Update README.md
Browse files
README.md
CHANGED
|
@@ -10,8 +10,6 @@ library_name: transformers
|
|
| 10 |
---
|
| 11 |
### CLIP ViT-L/14 finetune: SAE-informed adversarial training
|
| 12 |
|
| 13 |
-
### CLIP ViT-L/14 finetune: SAE-informed adversarial training
|
| 14 |
-
|
| 15 |
- SAE = Sparse autoencoder
|
| 16 |
- Accuracy ImageNet/ObjectNet [my GmP](https://huggingface.co/zer0int/CLIP-GmP-ViT-L-14): 91% > SAE (this): 89% > OpenAI pre-trained: 84.5%
|
| 17 |
- But, it's fun to use with e.g. Flux.1 - get the [Text-Encoder TE only version](https://huggingface.co/zer0int/CLIP-SAE-ViT-L-14/resolve/main/ViT-L-14-GmP-SAE-TE-only.safetensors?download=true) ⬇️ and try it!
|
|
|
|
| 10 |
---
|
| 11 |
### CLIP ViT-L/14 finetune: SAE-informed adversarial training
|
| 12 |
|
|
|
|
|
|
|
| 13 |
- SAE = Sparse autoencoder
|
| 14 |
- Accuracy ImageNet/ObjectNet [my GmP](https://huggingface.co/zer0int/CLIP-GmP-ViT-L-14): 91% > SAE (this): 89% > OpenAI pre-trained: 84.5%
|
| 15 |
- But, it's fun to use with e.g. Flux.1 - get the [Text-Encoder TE only version](https://huggingface.co/zer0int/CLIP-SAE-ViT-L-14/resolve/main/ViT-L-14-GmP-SAE-TE-only.safetensors?download=true) ⬇️ and try it!
|