config.json

{
  "attention_probs_dropout_prob": 0.1,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 32,
  "image_size": 30,
  "initializer_range": 0.02,
  "intermediate_size": 37,
  "layer_norm_eps": 1e-12,
  "model_type": "vit",
  "num_attention_heads": 4,
  "num_channels": 3,
  "num_hidden_layers": 5,
  "patch_size": 2,
  "transformers_version": "4.11.0.dev0",
  "transformers.js_config": {
    "free_dimension_overrides": {
      "batch_size": 1,
      "num_channels": 3,
      "height": 30,
      "width": 30
    }
  },
  "vocab_size": {},
  "architectures": [
    "ViTForImageClassification"
  ]
}