{
  "architectures": [
    "SamVisionModel"
  ],
  "attention_dropout": 0.0,
  "dtype": "float32",
  "global_attn_indexes": [
    2,
    5,
    8,
    11
  ],
  "hidden_act": "gelu",
  "hidden_size": 768,
  "image_size": 512,
  "initializer_range": 1e-10,
  "layer_norm_eps": 1e-06,
  "mlp_dim": 3072,
  "mlp_ratio": 4.0,
  "model_type": "sam_vision_model",
  "num_attention_heads": 12,
  "num_channels": 3,
  "num_hidden_layers": 12,
  "num_pos_feats": 128,
  "output_channels": 256,
  "patch_size": 16,
  "qkv_bias": true,
  "transformers_version": "5.0.0.dev0",
  "use_abs_pos": true,
  "use_rel_pos": true,
  "window_size": 7
}