{
  "model_type": "vit",
  "hidden_size": 768,
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "intermediate_size": 3072,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "attention_probs_dropout_prob": 0.1,
  "image_size": 128,
  "patch_size": 16,
  "num_channels": 3,
  "num_labels": 2
}