config.json

{
  "architectures": [
    "ViTForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "dtype": "float32",
  "encoder_stride": 16,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "BMW",
    "1": "Dodge",
    "2": "Ferrari",
    "3": "Ford",
    "4": "Jeep",
    "5": "Lamborghini",
    "6": "Porsche",
    "7": "Rolls-Royce",
    "8": "Toyota"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "BMW": 0,
    "Dodge": 1,
    "Ferrari": 2,
    "Ford": 3,
    "Jeep": 4,
    "Lamborghini": 5,
    "Porsche": 6,
    "Rolls-Royce": 7,
    "Toyota": 8
  },
  "layer_norm_eps": 1e-12,
  "model_type": "vit",
  "num_attention_heads": 12,
  "num_channels": 3,
  "num_hidden_layers": 12,
  "patch_size": 16,
  "pooler_act": "tanh",
  "pooler_output_size": 768,
  "problem_type": "single_label_classification",
  "qkv_bias": true,
  "transformers_version": "5.5.4",
  "use_cache": false
}