{
  "architectures": [
    "ViTForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "encoder_stride": 16,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "brands",
    "1": "groceries",
    "2": "handicrafts",
    "3": "indian product",
    "4": "local india",
    "5": "local markets",
    "6": "organic food",
    "7": "shops",
    "8": "store items",
    "9": "textiles"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "brands": "0",
    "groceries": "1",
    "handicrafts": "2",
    "indian product": "3",
    "local india": "4",
    "local markets": "5",
    "organic food": "6",
    "shops": "7",
    "store items": "8",
    "textiles": "9"
  },
  "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": "4.51.3"
}