{
  "_name_or_path": "dima806/fast_food_image_detection",
  "architectures": [
    "ViTForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "encoder_stride": 16,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "Burger",
    "1": "Taco",
    "2": "Baked Potato",
    "3": "Hot Dog",
    "4": "Pizza",
    "5": "Sandwich",
    "6": "Fries",
    "7": "Donut",
    "8": "Crispy Chicken",
    "9": "Taquito"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "Baked Potato": 2,
    "Burger": 0,
    "Crispy Chicken": 8,
    "Donut": 7,
    "Fries": 6,
    "Hot Dog": 3,
    "Pizza": 4,
    "Sandwich": 5,
    "Taco": 1,
    "Taquito": 9
  },
  "layer_norm_eps": 1e-12,
  "model_type": "vit",
  "num_attention_heads": 12,
  "num_channels": 3,
  "num_hidden_layers": 12,
  "patch_size": 16,
  "problem_type": "single_label_classification",
  "qkv_bias": true,
  "torch_dtype": "float32",
  "transformers_version": "4.38.2"
}