Instructions to use google/siglip-base-patch16-224 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use google/siglip-base-patch16-224 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="google/siglip-base-patch16-224") 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-patch16-224") model = AutoModelForZeroShotImageClassification.from_pretrained("google/siglip-base-patch16-224", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload processor
Browse files- tokenizer_config.json +0 -1
tokenizer_config.json
CHANGED
|
@@ -28,7 +28,6 @@
|
|
| 28 |
"pad_token": "</s>",
|
| 29 |
"processor_class": "SiglipProcessor",
|
| 30 |
"sp_model_kwargs": {},
|
| 31 |
-
"split_special_tokens": true,
|
| 32 |
"tokenizer_class": "SiglipTokenizer",
|
| 33 |
"unk_token": "<unk>"
|
| 34 |
}
|
|
|
|
| 28 |
"pad_token": "</s>",
|
| 29 |
"processor_class": "SiglipProcessor",
|
| 30 |
"sp_model_kwargs": {},
|
|
|
|
| 31 |
"tokenizer_class": "SiglipTokenizer",
|
| 32 |
"unk_token": "<unk>"
|
| 33 |
}
|