{
  "architectures": [
    "SiglipForImageClassification"
  ],
  "dtype": "float32",
  "id2label": {
    "0": "solid",
    "1": "environment"
  },
  "initializer_factor": 1.0,
  "label2id": {
    "environment": 1,
    "solid": 0
  },
  "model_type": "siglip",
  "problem_type": "single_label_classification",
  "text_config": {
    "attention_dropout": 0.0,
    "bos_token_id": 49406,
    "dtype": "float32",
    "eos_token_id": 49407,
    "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,
    "pad_token_id": 1,
    "projection_size": 768,
    "vocab_size": 256000
  },
  "transformers_version": "5.0.0",
  "use_cache": false,
  "vision_config": {
    "attention_dropout": 0.0,
    "dtype": "float32",
    "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
  }
}