Instructions to use Veritone/siglip2-base-patch16-384 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Veritone/siglip2-base-patch16-384 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="Veritone/siglip2-base-patch16-384") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("Veritone/siglip2-base-patch16-384") model = AutoModelForZeroShotImageClassification.from_pretrained("Veritone/siglip2-base-patch16-384", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Mirror google/siglip2-base-patch16-384
Browse files- config.json +8 -3
config.json
CHANGED
|
@@ -3,11 +3,16 @@
|
|
| 3 |
"model_type": "siglip",
|
| 4 |
"text_config": {
|
| 5 |
"model_type": "siglip_text_model",
|
| 6 |
-
"vocab_size": 256000
|
|
|
|
| 7 |
},
|
| 8 |
"transformers_version": "4.49.0.dev0",
|
| 9 |
"vision_config": {
|
| 10 |
"image_size": 384,
|
| 11 |
"model_type": "siglip_vision_model"
|
| 12 |
-
}
|
| 13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"model_type": "siglip",
|
| 4 |
"text_config": {
|
| 5 |
"model_type": "siglip_text_model",
|
| 6 |
+
"vocab_size": 256000,
|
| 7 |
+
"pad_token_id": 0
|
| 8 |
},
|
| 9 |
"transformers_version": "4.49.0.dev0",
|
| 10 |
"vision_config": {
|
| 11 |
"image_size": 384,
|
| 12 |
"model_type": "siglip_vision_model"
|
| 13 |
+
},
|
| 14 |
+
"architectures": [
|
| 15 |
+
"SiglipModel"
|
| 16 |
+
],
|
| 17 |
+
"max_position_embeddings": 64
|
| 18 |
+
}
|