{
  "architectures": [
    "ViTForImageClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "encoder_stride": 16,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 768,
  "id2label": {
    "0": "call",
    "1": "dislike",
    "2": "fist",
    "3": "four",
    "4": "like",
    "5": "mute",
    "6": "ok",
    "7": "one",
    "8": "palm",
    "9": "peace",
    "10": "peace_inverted",
    "11": "rock",
    "12": "stop",
    "13": "stop_inverted",
    "14": "three",
    "15": "three2",
    "16": "two_up",
    "17": "two_up_inverted"
  },
  "image_size": 224,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "label2id": {
    "call": 0,
    "dislike": 1,
    "fist": 2,
    "four": 3,
    "like": 4,
    "mute": 5,
    "ok": 6,
    "one": 7,
    "palm": 8,
    "peace": 9,
    "peace_inverted": 10,
    "rock": 11,
    "stop": 12,
    "stop_inverted": 13,
    "three": 14,
    "three2": 15,
    "two_up": 16,
    "two_up_inverted": 17
  },
  "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": "4.41.0"
}