{
  "architectures": [
    "EfficientVitForSemanticSegmentation"
  ],
  "attention_probs_dropout_prob": 0.0,
  "classifier_dropout_prob": 0.0,
  "decoder_hidden_size": 512,
  "decoder_layer_hidden_size": 128,
  "depths": [
    1,
    1,
    1,
    6,
    6
  ],
  "head_dim": 32,
  "hidden_dropout_prob": 0.0,
  "hidden_sizes": [
    32,
    64,
    160,
    256
  ],
  "initializer_range": 0.02,
  "layer_norm_eps": 1e-06,
  "model_type": "efficientvit",
  "num_channels": 3,
  "num_classes": 2,
  "num_stages": 4,
  "patch_size": [
    7,
    7
  ],
  "semantic_loss_ignore_index": -1,
  "torch_dtype": "float32",
  "transformers_version": "4.42.3",
  "widths": [
    32,
    64,
    128,
    256,
    512
  ]
}