Zero-Shot Image Classification
sentence-transformers
Safetensors
Chinese
siglip
trimmed
🇪🇺 Region: EU
Instructions to use alphaedge-ai/siglip2-giant-opt-patch16-384-zho-16384 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use alphaedge-ai/siglip2-giant-opt-patch16-384-zho-16384 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("alphaedge-ai/siglip2-giant-opt-patch16-384-zho-16384") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "google/siglip2-giant-opt-patch16-384", | |
| "architectures": [ | |
| "SiglipModel" | |
| ], | |
| "initializer_factor": 1.0, | |
| "model_type": "siglip", | |
| "text_config": { | |
| "hidden_size": 1152, | |
| "intermediate_size": 4304, | |
| "model_type": "siglip_text_model", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 27, | |
| "projection_size": 1536, | |
| "vocab_size": 16384 | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.46.3", | |
| "vision_config": { | |
| "hidden_size": 1536, | |
| "image_size": 384, | |
| "intermediate_size": 6144, | |
| "model_type": "siglip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 40 | |
| } | |
| } |