{
  "architectures": [
    "SiglipForImageClassification"
  ],
  "dtype": "float16",
  "id2label": {
    "0": "3AA",
    "1": "3AB",
    "2": "3AC",
    "3": "3BA",
    "4": "3BB",
    "5": "3BC",
    "6": "3CA",
    "7": "3CB",
    "8": "3CC",
    "9": "4AA",
    "10": "4AB",
    "11": "4AC",
    "12": "4BA",
    "13": "4BB",
    "14": "4BC",
    "15": "4CA",
    "16": "4CB",
    "17": "4CC",
    "18": "5AA",
    "19": "5AB",
    "20": "5AC",
    "21": "5BA",
    "22": "5BB",
    "23": "5BC"
  },
  "initializer_factor": 1.0,
  "label2id": {
    "3AA": 0,
    "3AB": 1,
    "3AC": 2,
    "3BA": 3,
    "3BB": 4,
    "3BC": 5,
    "3CA": 6,
    "3CB": 7,
    "3CC": 8,
    "4AA": 9,
    "4AB": 10,
    "4AC": 11,
    "4BA": 12,
    "4BB": 13,
    "4BC": 14,
    "4CA": 15,
    "4CB": 16,
    "4CC": 17,
    "5AA": 18,
    "5AB": 19,
    "5AC": 20,
    "5BA": 21,
    "5BB": 22,
    "5BC": 23
  },
  "model_type": "siglip",
  "problem_type": "single_label_classification",
  "text_config": {
    "attention_dropout": 0.0,
    "dtype": "float16",
    "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,
    "vocab_size": 256000
  },
  "transformers_version": "4.56.1",
  "vision_config": {
    "attention_dropout": 0.0,
    "dtype": "float16",
    "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
  }
}