{
  "architectures": [
    "SiglipForImageClassification"
  ],
  "id2label": {
    "0": "Annual Crop",
    "1": "Forest",
    "2": "Herbaceous Vegetation",
    "3": "Highway",
    "4": "Industrial",
    "5": "Pasture",
    "6": "Permanent Crop",
    "7": "Residential",
    "8": "River",
    "9": "Sea Lake"
  },
  "initializer_factor": 1.0,
  "label2id": {
    "Annual Crop": 0,
    "Forest": 1,
    "Herbaceous Vegetation": 2,
    "Highway": 3,
    "Industrial": 4,
    "Pasture": 5,
    "Permanent Crop": 6,
    "Residential": 7,
    "River": 8,
    "Sea Lake": 9
  },
  "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": "4.51.0.dev0",
  "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"
  }
}