{
  "architectures": [
    "SiglipForImageClassification"
  ],
  "id2label": {
    "0": "Advertisement-Doc",
    "1": "Hand-Written-Doc",
    "2": "Invoice-Doc",
    "3": "Letter-Doc",
    "4": "News-Article-Doc",
    "5": "Resume-Doc"
  },
  "initializer_factor": 1.0,
  "label2id": {
    "Advertisement-Doc": 0,
    "Hand-Written-Doc": 1,
    "Invoice-Doc": 2,
    "Letter-Doc": 3,
    "News-Article-Doc": 4,
    "Resume-Doc": 5
  },
  "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"
  }
}