Instructions to use nzs234/siglip2-so400m-aesthetic-scorer-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nzs234/siglip2-so400m-aesthetic-scorer-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-classification", model="nzs234/siglip2-so400m-aesthetic-scorer-v1") pipe("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("nzs234/siglip2-so400m-aesthetic-scorer-v1", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "SiglipModel" | |
| ], | |
| "dtype": "float32", | |
| "initializer_factor": 1.0, | |
| "model_type": "siglip", | |
| "text_config": { | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 49406, | |
| "dtype": "float32", | |
| "eos_token_id": 49407, | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "intermediate_size": 4304, | |
| "layer_norm_eps": 1e-06, | |
| "max_position_embeddings": 64, | |
| "model_type": "siglip_text_model", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 27, | |
| "pad_token_id": 1, | |
| "projection_size": 1152, | |
| "vocab_size": 256000 | |
| }, | |
| "transformers_version": "5.2.0", | |
| "vision_config": { | |
| "attention_dropout": 0.0, | |
| "dtype": "float32", | |
| "hidden_act": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "image_size": 512, | |
| "intermediate_size": 4304, | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "siglip_vision_model", | |
| "num_attention_heads": 16, | |
| "num_channels": 3, | |
| "num_hidden_layers": 27, | |
| "patch_size": 16 | |
| } | |
| } | |