{
    "architectures": ["ViTForImageClassification"],
    "hidden_size": 768,
    "num_hidden_layers": 12,
    "num_attention_heads": 12,
    "intermediate_size": 3072,
    "hidden_act": "gelu",
    "initializer_range": 0.02,
    "vocab_size": 30522,
    "type_vocab_size": 2,
    "max_position_embeddings": 512,
    "model_type": "vit"
}