{
  "architectures": [
    "DinatForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "depths": [
    1,
    2,
    1
  ],
  "dilations": [
    [
      3
    ],
    [
      1,
      2
    ],
    [
      1
    ]
  ],
  "drop_path_rate": 0.1,
  "embed_dim": 16,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 64,
  "id2label": {
    "0": "LABEL_0",
    "1": "LABEL_1",
    "2": "LABEL_2",
    "3": "LABEL_3",
    "4": "LABEL_4",
    "5": "LABEL_5",
    "6": "LABEL_6",
    "7": "LABEL_7",
    "8": "LABEL_8",
    "9": "LABEL_9"
  },
  "image_size": 64,
  "initializer_range": 0.02,
  "kernel_size": 3,
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_2": 2,
    "LABEL_3": 3,
    "LABEL_4": 4,
    "LABEL_5": 5,
    "LABEL_6": 6,
    "LABEL_7": 7,
    "LABEL_8": 8,
    "LABEL_9": 9
  },
  "layer_norm_eps": 1e-05,
  "layer_scale_init_value": 0.0,
  "mlp_ratio": 2.0,
  "model_type": "dinat",
  "num_channels": 3,
  "num_heads": [
    2,
    4,
    8
  ],
  "num_layers": 3,
  "out_features": [
    "stage1",
    "stage2"
  ],
  "patch_norm": true,
  "patch_size": 4,
  "qkv_bias": true,
  "stage_names": [
    "stem",
    "stage1",
    "stage2",
    "stage3"
  ],
  "torch_dtype": "float32",
  "transformers_version": "4.28.0.dev0"
}