Zero-Shot Image Classification
Transformers
Safetensors
tipsv2
feature-extraction
vision
contrastive-learning
zero-shot
custom_code
Instructions to use nebulette/tipsv2-b14-vision-module with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nebulette/tipsv2-b14-vision-module with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="nebulette/tipsv2-b14-vision-module", trust_remote_code=True) pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nebulette/tipsv2-b14-vision-module", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -67,6 +67,8 @@ rgb = 1 / (1 + np.exp(-2.0 * rgb)) # sigmoid for [0, 1] range with good contras
|
|
| 67 |
print(rgb.shape) # (32, 32, 3) — PCA of patch features as RGB
|
| 68 |
```
|
| 69 |
|
|
|
|
|
|
|
| 70 |
## Model details
|
| 71 |
|
| 72 |
- **Architecture**: ViT vision encoder (12 layers) + Transformer text encoder (12 layers)
|
|
|
|
| 67 |
print(rgb.shape) # (32, 32, 3) — PCA of patch features as RGB
|
| 68 |
```
|
| 69 |
|
| 70 |
+

|
| 71 |
+
|
| 72 |
## Model details
|
| 73 |
|
| 74 |
- **Architecture**: ViT vision encoder (12 layers) + Transformer text encoder (12 layers)
|