{
  "architectures": [
    "CvtForImageClassification"
  ],
  "attention_drop_rate": [
    0.0,
    0.0,
    0.0
  ],
  "cls_token": [
    false,
    false,
    true
  ],
  "depth": [
    1,
    4,
    16
  ],
  "drop_path_rate": [
    0.0,
    0.0,
    0.1
  ],
  "drop_rate": [
    0.0,
    0.0,
    0.0
  ],
  "embed_dim": [
    64,
    192,
    384
  ],
  "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",
    "10": "LABEL_10",
    "11": "LABEL_11",
    "12": "LABEL_12",
    "13": "LABEL_13",
    "14": "LABEL_14"
  },
  "image_size": 384,
  "initializer_range": 0.02,
  "kernel_qkv": [
    3,
    3,
    3
  ],
  "label2id": {
    "LABEL_0": 0,
    "LABEL_1": 1,
    "LABEL_10": 10,
    "LABEL_11": 11,
    "LABEL_12": 12,
    "LABEL_13": 13,
    "LABEL_14": 14,
    "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-12,
  "mlp_ratio": [
    4.0,
    4.0,
    4.0
  ],
  "model_type": "cvt",
  "num_channels": 3,
  "num_heads": [
    1,
    3,
    6
  ],
  "num_stages": 3,
  "padding_kv": [
    1,
    1,
    1
  ],
  "padding_q": [
    1,
    1,
    1
  ],
  "patch_padding": [
    2,
    1,
    1
  ],
  "patch_sizes": [
    7,
    3,
    3
  ],
  "patch_stride": [
    4,
    2,
    2
  ],
  "pos_embed": [
    false,
    false,
    false
  ],
  "problem_type": "multi_label_classification",
  "qkv_bias": [
    true,
    true,
    true
  ],
  "qkv_projection_method": [
    "dw_bn",
    "dw_bn",
    "dw_bn"
  ],
  "stride_kv": [
    2,
    2,
    2
  ],
  "stride_q": [
    1,
    1,
    1
  ],
  "torch_dtype": "float32",
  "transformers_version": "4.52.3"
}