config.json

{
  "architectures": [
    "SiglipForImageClassification"
  ],
  "id2label": {
    "0": "brick",
    "1": "carpet",
    "2": "ceramic",
    "3": "fabric",
    "4": "foliage",
    "5": "food",
    "6": "glass",
    "7": "hair",
    "8": "leather",
    "9": "metal",
    "10": "mirror",
    "11": "other",
    "12": "painted",
    "13": "paper",
    "14": "plastic",
    "15": "polishedstone",
    "16": "skin",
    "17": "sky",
    "18": "stone",
    "19": "tile",
    "20": "wallpaper",
    "21": "water",
    "22": "wood"
  },
  "initializer_factor": 1.0,
  "label2id": {
    "brick": 0,
    "carpet": 1,
    "ceramic": 2,
    "fabric": 3,
    "foliage": 4,
    "food": 5,
    "glass": 6,
    "hair": 7,
    "leather": 8,
    "metal": 9,
    "mirror": 10,
    "other": 11,
    "painted": 12,
    "paper": 13,
    "plastic": 14,
    "polishedstone": 15,
    "skin": 16,
    "sky": 17,
    "stone": 18,
    "tile": 19,
    "wallpaper": 20,
    "water": 21,
    "wood": 22
  },
  "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"
  }
}