{
  "architectures": ["ViTForImageClassification"],
  "hidden_size": 768,
  "num_hidden_layers": 12,
  "num_attention_heads": 12,
  "intermediate_size": 3072,
  "patch_size": 4, 
  "image_size": 28,
  "num_channels": 1,
  "id2label": {"0": "0", "1": "1", "2": "2", "3": "3", "4": "4", "5": "5", "6": "6", "7": "7", "8": "8", "9": "9"},
  "label2id": {"0": 0, "1": 1, "2": 2, "3": 3, "4": 4, "5": 5, "6": 6, "7": 7, "8": 8, "9": 9},
  "model_type": "vit"
}