{ "architectures": [ "SiglipForImageClassification" ], "id2label": { "0": "Apple Style", "1": "DoCoMo Style", "2": "Facebook Style", "3": "Gmail Style", "4": "Google Style", "5": "JoyPixels Style", "6": "KDDI Style", "7": "Samsung Style", "8": "SoftBank Style", "9": "Twitter Style", "10": "Windows Style" }, "initializer_factor": 1.0, "label2id": { "Apple Style": 0, "DoCoMo Style": 1, "Facebook Style": 2, "Gmail Style": 3, "Google Style": 4, "JoyPixels Style": 5, "KDDI Style": 6, "Samsung Style": 7, "SoftBank Style": 8, "Twitter Style": 9, "Windows Style": 10 }, "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": "4.50.2", "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" } }