Instructions to use google/siglip-base-patch16-256 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/siglip-base-patch16-256 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="google/siglip-base-patch16-256") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# Load model directly from transformers import AutoProcessor, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("google/siglip-base-patch16-256") model = AutoModelForZeroShotImageClassification.from_pretrained("google/siglip-base-patch16-256", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -83,6 +83,13 @@ Texts are tokenized and padded to the same length (64 tokens).
|
|
| 83 |
|
| 84 |
The model was trained on 16 TPU-v4 chips for three days.
|
| 85 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 86 |
### BibTeX entry and citation info
|
| 87 |
|
| 88 |
```bibtex
|
|
|
|
| 83 |
|
| 84 |
The model was trained on 16 TPU-v4 chips for three days.
|
| 85 |
|
| 86 |
+
## Evaluation results
|
| 87 |
+
|
| 88 |
+
Evaluation of SigLIP compared to CLIP is shown below (taken from the paper).
|
| 89 |
+
|
| 90 |
+
<img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/siglip_table.jpeg"
|
| 91 |
+
alt="drawing" width="600"/>
|
| 92 |
+
|
| 93 |
### BibTeX entry and citation info
|
| 94 |
|
| 95 |
```bibtex
|