{
  "_name_or_path": "google/vit-base-patch16-224",
  "architectures": [
    "ViTForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "encoder_stride": 16,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "biryani",
    "1": "cholebhature",
    "10": "pakora",
    "11": "paneer",
    "12": "panipuri",
    "13": "pavbhaji",
    "14": "vadapav",
    "2": "dabeli",
    "3": "dal",
    "4": "dhokla",
    "5": "dosa",
    "6": "jalebi",
    "7": "kathiroll",
    "8": "kofta",
    "9": "naan"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "biryani": "0",
    "cholebhature": "1",
    "dabeli": "2",
    "dal": "3",
    "dhokla": "4",
    "dosa": "5",
    "jalebi": "6",
    "kathiroll": "7",
    "kofta": "8",
    "naan": "9",
    "pakora": "10",
    "paneer": "11",
    "panipuri": "12",
    "pavbhaji": "13",
    "vadapav": "14"
  },
  "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"
}