Instructions to use Veritone/siglip2-large-patch16-512 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Veritone/siglip2-large-patch16-512 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="Veritone/siglip2-large-patch16-512") 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-large-patch16-512") model = AutoModelForZeroShotImageClassification.from_pretrained("Veritone/siglip2-large-patch16-512", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from Veritone/siglip2-large-patch16-512: direct link, hf CLI and curl.
- Browser
- Download file 636 Bytes
-
https://huggingface.co/Veritone/siglip2-large-patch16-512/resolve/main/config.json
- Command line
-
hf download hf://Veritone/siglip2-large-patch16-512/config.json
-
curl -L -o config.json https://huggingface.co/Veritone/siglip2-large-patch16-512/resolve/main/config.json
636 Bytes
| { | |
| "initializer_factor": 1.0, | |
| "model_type": "siglip", | |
| "text_config": { | |
| "hidden_size": 1024, | |
| "intermediate_size": 4096, | |
| "model_type": "siglip_text_model", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "projection_size": 1024, | |
| "vocab_size": 256000, | |
| "pad_token_id": 0 | |
| }, | |
| "transformers_version": "4.49.0.dev0", | |
| "vision_config": { | |
| "hidden_size": 1024, | |
| "image_size": 512, | |
| "intermediate_size": 4096, | |
| "model_type": "siglip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24 | |
| }, | |
| "architectures": [ | |
| "SiglipModel" | |
| ], | |
| "max_position_embeddings": 64 | |
| } |