{ "architectures": [ "SiglipForImageClassification" ], "id2label": { "0": "age 01-10", "1": "age 11-20", "2": "age 21-30", "3": "age 31-40", "4": "age 41-55", "5": "age 56-65", "6": "age 66-80", "7": "age 80 +" }, "initializer_factor": 1.0, "label2id": { "age 01-10": 0, "age 11-20": 1, "age 21-30": 2, "age 31-40": 3, "age 41-55": 4, "age 56-65": 5, "age 66-80": 6, "age 80 +": 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": "4.50.0", "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" } }