Instructions to use google/siglip-base-patch16-256-multilingual with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/siglip-base-patch16-256-multilingual 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-multilingual") 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-multilingual") model = AutoModelForZeroShotImageClassification.from_pretrained("google/siglip-base-patch16-256-multilingual") - Notebooks
- Google Colab
- Kaggle
Upload model
Browse files- config.json +17 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"SiglipModel"
|
| 4 |
+
],
|
| 5 |
+
"initializer_factor": 1.0,
|
| 6 |
+
"model_type": "siglip",
|
| 7 |
+
"text_config": {
|
| 8 |
+
"model_type": "siglip_text_model",
|
| 9 |
+
"vocab_size": 250000
|
| 10 |
+
},
|
| 11 |
+
"torch_dtype": "float32",
|
| 12 |
+
"transformers_version": "4.37.0.dev0",
|
| 13 |
+
"vision_config": {
|
| 14 |
+
"image_size": 256,
|
| 15 |
+
"model_type": "siglip_vision_model"
|
| 16 |
+
}
|
| 17 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:00df88d823790b34a4d2d0047803ffabd47497ae724fd6659b1533dd793255be
|
| 3 |
+
size 1482553200
|