config.json

{
  "architectures": [
    "SiglipModel"
  ],
  "dtype": "float32",
  "initializer_factor": 1.0,
  "model_type": "siglip",
  "text_config": {
    "attention_dropout": 0.0,
    "dtype": "float32",
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 1024,
    "intermediate_size": 4096,
    "layer_norm_eps": 1e-06,
    "max_position_embeddings": 64,
    "model_type": "siglip_text_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 24,
    "projection_size": 1024,
    "vocab_size": 32000
  },
  "transformers_version": "4.56.0",
  "vision_config": {
    "attention_dropout": 0.0,
    "dtype": "float32",
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 1024,
    "image_size": 256,
    "intermediate_size": 4096,
    "layer_norm_eps": 1e-06,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 24,
    "patch_size": 16
  }
}