Image Feature Extraction
Transformers
Safetensors
siglip
zero-shot-image-classification
siglip2
vision
image-embeddings
pet-recognition
Instructions to use AvitoTech/SigLIP2-Base-for-animal-identification with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AvitoTech/SigLIP2-Base-for-animal-identification with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-feature-extraction", model="AvitoTech/SigLIP2-Base-for-animal-identification")# Load model directly from transformers import AutoProcessor, AutoModelForZeroShotImageClassification processor = AutoProcessor.from_pretrained("AvitoTech/SigLIP2-Base-for-animal-identification") model = AutoModelForZeroShotImageClassification.from_pretrained("AvitoTech/SigLIP2-Base-for-animal-identification", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "SiglipModel" | |
| ], | |
| "model_type": "siglip", | |
| "projection_dim": 768, | |
| "text_config": { | |
| "hidden_size": 768, | |
| "intermediate_size": 3072, | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "model_type": "siglip_text_model", | |
| "vocab_size": 256000 | |
| }, | |
| "vision_config": { | |
| "hidden_size": 768, | |
| "image_size": 224, | |
| "intermediate_size": 3072, | |
| "num_attention_heads": 12, | |
| "num_channels": 3, | |
| "num_hidden_layers": 12, | |
| "patch_size": 16, | |
| "model_type": "siglip_vision_model" | |
| } | |
| } |