Instructions to use LEAF-CLIP/OpenCLIP-ViT-bigG-rho50-k1-constrained with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LEAF-CLIP/OpenCLIP-ViT-bigG-rho50-k1-constrained with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="LEAF-CLIP/OpenCLIP-ViT-bigG-rho50-k1-constrained")# Load model directly from transformers import AutoProcessor, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("LEAF-CLIP/OpenCLIP-ViT-bigG-rho50-k1-constrained") model = AutoModelForZeroShotImageClassification.from_pretrained("LEAF-CLIP/OpenCLIP-ViT-bigG-rho50-k1-constrained", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,6 +6,7 @@ datasets:
|
|
| 6 |
base_model:
|
| 7 |
- laion/CLIP-ViT-bigG-14-laion2B-39B-b160k
|
| 8 |
---
|
|
|
|
| 9 |
|
| 10 |
Model Initialized from `laion/CLIP-ViT-bigG-14-laion2B-39B-b160k`. The text encoder is finetuned with LEAF at $k=1$ with $\rho=50$ and semantic constraints.
|
| 11 |
|
|
|
|
| 6 |
base_model:
|
| 7 |
- laion/CLIP-ViT-bigG-14-laion2B-39B-b160k
|
| 8 |
---
|
| 9 |
+
[[Paper]](https://www.arxiv.org/abs/2506.03355) [[Code]](https://github.com/LIONS-EPFL/LEAF)
|
| 10 |
|
| 11 |
Model Initialized from `laion/CLIP-ViT-bigG-14-laion2B-39B-b160k`. The text encoder is finetuned with LEAF at $k=1$ with $\rho=50$ and semantic constraints.
|
| 12 |
|