{ "architectures": [ "SiglipForImageClassification" ], "id2label": { "0": "Casual", "1": "Ethnic", "2": "Formal", "3": "Home", "4": "Party", "5": "Smart Casual", "6": "Sports", "7": "Travel" }, "initializer_factor": 1.0, "label2id": { "Casual": 0, "Ethnic": 1, "Formal": 2, "Home": 3, "Party": 4, "Smart Casual": 5, "Sports": 6, "Travel": 7 }, "model_type": "siglip", "problem_type": "single_label_classification", "text_config": { "attention_dropout": 0.0, "hidden_act": "gelu_pytorch_tanh", "hidden_size": 768, "intermediate_size": 3072, "layer_norm_eps": 1e-06, "max_position_embeddings": 64, "model_type": "siglip_text_model", "num_attention_heads": 12, "num_hidden_layers": 12, "projection_size": 768, "torch_dtype": "float32", "vocab_size": 256000 }, "torch_dtype": "float32", "transformers_version": "4.50.3", "vision_config": { "attention_dropout": 0.0, "hidden_act": "gelu_pytorch_tanh", "hidden_size": 768, "image_size": 224, "intermediate_size": 3072, "layer_norm_eps": 1e-06, "model_type": "siglip_vision_model", "num_attention_heads": 12, "num_channels": 3, "num_hidden_layers": 12, "patch_size": 16, "torch_dtype": "float32" } }