config.json

{
  "model_type": "vit",
  "hidden_size": 768,
  "num_hidden_layers": 12,
  "num_attention_heads": 12,
  "intermediate_size": 3072,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "attention_probs_dropout_prob": 0.0,
  "initializer_range": 0.02,
  "layer_norm_eps": 1e-12,
  "image_size": 224,
  "patch_size": 16,
  "num_channels": 3,
  "qkv_bias": true,
  "encoder_stride": 16
}