{
  "architectures": [
    "ViTForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "encoder_stride": 16,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "Black-grass",
    "1": "Charlock",
    "2": "Cleavers",
    "3": "Common Chickweed",
    "4": "Common wheat",
    "5": "Fat Hen",
    "6": "Loose Silky-bent",
    "7": "Maize",
    "8": "Scentless Mayweed",
    "9": "Shepherds Purse",
    "10": "Small-flowered Cranesbill",
    "11": "Sugar beet"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "Black-grass": 0,
    "Charlock": 1,
    "Cleavers": 2,
    "Common Chickweed": 3,
    "Common wheat": 4,
    "Fat Hen": 5,
    "Loose Silky-bent": 6,
    "Maize": 7,
    "Scentless Mayweed": 8,
    "Shepherds Purse": 9,
    "Small-flowered Cranesbill": 10,
    "Sugar beet": 11
  },
  "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,
  "qkv_bias": true,
  "torch_dtype": "float32",
  "transformers_version": "4.51.3"
}