{
  "architectures": [
    "ViTForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "dtype": "float32",
  "encoder_stride": 16,
  "finetuning_task": "image-classification",
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "Dosehri",
    "1": "Sindhri",
    "2": "Fajri",
    "3": "Anwar Ratool",
    "4": "Chaunsa (White)",
    "5": "Langra",
    "6": "Chaunsa (Black)",
    "7": "Chaunsa (Summer Bahisht)"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "Anwar Ratool": "3",
    "Chaunsa (Black)": "6",
    "Chaunsa (Summer Bahisht)": "7",
    "Chaunsa (White)": "4",
    "Dosehri": "0",
    "Fajri": "2",
    "Langra": "5",
    "Sindhri": "1"
  },
  "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,
  "transformers_version": "4.56.1"
}