{
  "_name_or_path": "google/vit-base-patch16-224-in21k",
  "architectures": [
    "ViTForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "encoder_stride": 16,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "Crispy Chicken",
    "1": "burger",
    "2": "chole_bhature",
    "3": "chai",
    "4": "chicken_curry",
    "5": "cheesecake",
    "6": "Baked Potato",
    "7": "apple_pie",
    "8": "dal_makhani",
    "9": "butter_naan",
    "10": "dhokla",
    "11": "chapati"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "Baked Potato": 6,
    "Crispy Chicken": 0,
    "apple_pie": 7,
    "burger": 1,
    "butter_naan": 9,
    "chai": 3,
    "chapati": 11,
    "cheesecake": 5,
    "chicken_curry": 4,
    "chole_bhature": 2,
    "dal_makhani": 8,
    "dhokla": 10
  },
  "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": "4.39.3"
}