config.json

{
  "architectures": [
    "SiglipRegionModel"
  ],
  "conditional_layer": 0,
  "decoder_attention_dropout": 0.0,
  "decoder_hidden_act": "quick_gelu",
  "decoder_intermediate_size": 2048,
  "decoder_num_attention_heads": 4,
  "extract_layers": [
    3,
    6,
    9
  ],
  "initializer_factor": 1.0,
  "logit_scale_init_value": 2.6592,
  "model_type": "siglipseg",
  "projection_dim": 512,
  "reduce_dim": 1152,
  "text_config": {
    "attention_dropout": 0.0,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 1152,
    "intermediate_size": 4304,
    "layer_norm_eps": 1e-06,
    "max_position_embeddings": 64,
    "model_type": "siglip_text_model",
    "num_attention_heads": 16,
    "num_hidden_layers": 27,
    "projection_size": 1152,
    "torch_dtype": "float32",
    "vocab_size": 32000
  },
  "torch_dtype": "float32",
  "transformers_version": "4.52.4",
  "use_cache": true,
  "use_complex_transposed_convolution": false,
  "vision_config": {
    "attention_dropout": 0.0,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 1152,
    "image_size": 384,
    "intermediate_size": 4304,
    "layer_norm_eps": 1e-06,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 16,
    "num_channels": 3,
    "num_hidden_layers": 27,
    "patch_size": 14,
    "torch_dtype": "float32"
  }
}