config.json

{
  "architectures": [
    "SiglipForImageClassification"
  ],
  "id2label": {
    "0": "A",
    "1": "B",
    "2": "C",
    "3": "D",
    "4": "E",
    "5": "F",
    "6": "G",
    "7": "H",
    "8": "I",
    "9": "J",
    "10": "K",
    "11": "L",
    "12": "M",
    "13": "N",
    "14": "O",
    "15": "P",
    "16": "Q",
    "17": "R",
    "18": "S",
    "19": "T",
    "20": "U",
    "21": "V",
    "22": "W",
    "23": "X",
    "24": "Y",
    "25": "Z"
  },
  "initializer_factor": 1.0,
  "label2id": {
    "A": 0,
    "B": 1,
    "C": 2,
    "D": 3,
    "E": 4,
    "F": 5,
    "G": 6,
    "H": 7,
    "I": 8,
    "J": 9,
    "K": 10,
    "L": 11,
    "M": 12,
    "N": 13,
    "O": 14,
    "P": 15,
    "Q": 16,
    "R": 17,
    "S": 18,
    "T": 19,
    "U": 20,
    "V": 21,
    "W": 22,
    "X": 23,
    "Y": 24,
    "Z": 25
  },
  "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"
  }
}