{
  "architectures": [
    "ViTForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "encoder_stride": 16,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "Abuse",
    "1": "Arrest",
    "2": "Arson",
    "3": "Assault",
    "4": "Burglary",
    "5": "Explosion",
    "6": "Fighting",
    "7": "Normal",
    "8": "RoadAccidents",
    "9": "Robbery",
    "10": "Shooting",
    "11": "Shoplifting",
    "12": "Stealing",
    "13": "Vandalism"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "Abuse": 0,
    "Arrest": 1,
    "Arson": 2,
    "Assault": 3,
    "Burglary": 4,
    "Explosion": 5,
    "Fighting": 6,
    "Normal": 7,
    "RoadAccidents": 8,
    "Robbery": 9,
    "Shooting": 10,
    "Shoplifting": 11,
    "Stealing": 12,
    "Vandalism": 13
  },
  "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,
  "torch_dtype": "float32",
  "transformers_version": "4.53.3"
}