{
  "architectures": [
    "SiglipForImageClassification"
  ],
  "id2label": {
    "0": "barn",
    "1": "baseball_bat",
    "2": "basket",
    "3": "beach",
    "4": "bear",
    "5": "beard",
    "6": "bee",
    "7": "bird",
    "8": "blueberry",
    "9": "bowtie",
    "10": "bracelet",
    "11": "brain",
    "12": "bread",
    "13": "broccoli",
    "14": "bus",
    "15": "butterfly",
    "16": "circle",
    "17": "cloud",
    "18": "cruise_ship",
    "19": "dolphin",
    "20": "dumbbell",
    "21": "elephant",
    "22": "eye",
    "23": "eyeglasses",
    "24": "feather",
    "25": "fish",
    "26": "flower",
    "27": "foot",
    "28": "frog",
    "29": "giraffe",
    "30": "goatee",
    "31": "golf_club",
    "32": "grapes",
    "33": "grass",
    "34": "guitar",
    "35": "hamburger",
    "36": "hand",
    "37": "hat",
    "38": "headphones",
    "39": "helicopter",
    "40": "hexagon",
    "41": "hockey_stick",
    "42": "horse",
    "43": "hourglass",
    "44": "house",
    "45": "ice_cream",
    "46": "jacket",
    "47": "ladder",
    "48": "leg",
    "49": "lipstick",
    "50": "megaphone",
    "51": "monkey",
    "52": "moon",
    "53": "mushroom",
    "54": "necklace",
    "55": "owl",
    "56": "panda",
    "57": "pear",
    "58": "peas",
    "59": "penguin",
    "60": "pig",
    "61": "pillow",
    "62": "pineapple",
    "63": "pizza",
    "64": "pool",
    "65": "popsicle",
    "66": "rabbit",
    "67": "rhinoceros",
    "68": "rifle",
    "69": "river",
    "70": "sailboat",
    "71": "sandwich",
    "72": "sea_turtle",
    "73": "shark",
    "74": "shoe",
    "75": "skyscraper",
    "76": "snorkel",
    "77": "snowman",
    "78": "soccer_ball",
    "79": "speedboat",
    "80": "spider",
    "81": "spoon",
    "82": "square",
    "83": "squirrel",
    "84": "stethoscope",
    "85": "strawberry",
    "86": "streetlight",
    "87": "submarine",
    "88": "suitcase",
    "89": "sun",
    "90": "sweater",
    "91": "sword",
    "92": "table",
    "93": "teapot",
    "94": "teddy-bear",
    "95": "telephone",
    "96": "tent",
    "97": "The_Eiffel_Tower",
    "98": "The_Great_Wall_of_China",
    "99": "The_Mona_Lisa",
    "100": "tiger",
    "101": "toaster",
    "102": "tooth",
    "103": "tornado",
    "104": "tractor",
    "105": "train",
    "106": "tree",
    "107": "triangle",
    "108": "trombone",
    "109": "truck",
    "110": "trumpet",
    "111": "umbrella",
    "112": "vase",
    "113": "violin",
    "114": "watermelon",
    "115": "whale",
    "116": "windmill",
    "117": "wine_glass",
    "118": "yoga",
    "119": "zebra",
    "120": "zigzag"
  },
  "initializer_factor": 1.0,
  "label2id": {
    "The_Eiffel_Tower": 97,
    "The_Great_Wall_of_China": 98,
    "The_Mona_Lisa": 99,
    "barn": 0,
    "baseball_bat": 1,
    "basket": 2,
    "beach": 3,
    "bear": 4,
    "beard": 5,
    "bee": 6,
    "bird": 7,
    "blueberry": 8,
    "bowtie": 9,
    "bracelet": 10,
    "brain": 11,
    "bread": 12,
    "broccoli": 13,
    "bus": 14,
    "butterfly": 15,
    "circle": 16,
    "cloud": 17,
    "cruise_ship": 18,
    "dolphin": 19,
    "dumbbell": 20,
    "elephant": 21,
    "eye": 22,
    "eyeglasses": 23,
    "feather": 24,
    "fish": 25,
    "flower": 26,
    "foot": 27,
    "frog": 28,
    "giraffe": 29,
    "goatee": 30,
    "golf_club": 31,
    "grapes": 32,
    "grass": 33,
    "guitar": 34,
    "hamburger": 35,
    "hand": 36,
    "hat": 37,
    "headphones": 38,
    "helicopter": 39,
    "hexagon": 40,
    "hockey_stick": 41,
    "horse": 42,
    "hourglass": 43,
    "house": 44,
    "ice_cream": 45,
    "jacket": 46,
    "ladder": 47,
    "leg": 48,
    "lipstick": 49,
    "megaphone": 50,
    "monkey": 51,
    "moon": 52,
    "mushroom": 53,
    "necklace": 54,
    "owl": 55,
    "panda": 56,
    "pear": 57,
    "peas": 58,
    "penguin": 59,
    "pig": 60,
    "pillow": 61,
    "pineapple": 62,
    "pizza": 63,
    "pool": 64,
    "popsicle": 65,
    "rabbit": 66,
    "rhinoceros": 67,
    "rifle": 68,
    "river": 69,
    "sailboat": 70,
    "sandwich": 71,
    "sea_turtle": 72,
    "shark": 73,
    "shoe": 74,
    "skyscraper": 75,
    "snorkel": 76,
    "snowman": 77,
    "soccer_ball": 78,
    "speedboat": 79,
    "spider": 80,
    "spoon": 81,
    "square": 82,
    "squirrel": 83,
    "stethoscope": 84,
    "strawberry": 85,
    "streetlight": 86,
    "submarine": 87,
    "suitcase": 88,
    "sun": 89,
    "sweater": 90,
    "sword": 91,
    "table": 92,
    "teapot": 93,
    "teddy-bear": 94,
    "telephone": 95,
    "tent": 96,
    "tiger": 100,
    "toaster": 101,
    "tooth": 102,
    "tornado": 103,
    "tractor": 104,
    "train": 105,
    "tree": 106,
    "triangle": 107,
    "trombone": 108,
    "truck": 109,
    "trumpet": 110,
    "umbrella": 111,
    "vase": 112,
    "violin": 113,
    "watermelon": 114,
    "whale": 115,
    "windmill": 116,
    "wine_glass": 117,
    "yoga": 118,
    "zebra": 119,
    "zigzag": 120
  },
  "model_type": "siglip",
  "problem_type": "single_label_classification",
  "text_config": {
    "attention_dropout": 0.0,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 768,
    "intermediate_size": 3072,
    "layer_norm_eps": 1e-06,
    "max_position_embeddings": 64,
    "model_type": "siglip_text_model",
    "num_attention_heads": 12,
    "num_hidden_layers": 12,
    "projection_size": 768,
    "torch_dtype": "float32",
    "vocab_size": 256000
  },
  "torch_dtype": "float32",
  "transformers_version": "4.51.0.dev0",
  "vision_config": {
    "attention_dropout": 0.0,
    "hidden_act": "gelu_pytorch_tanh",
    "hidden_size": 768,
    "image_size": 224,
    "intermediate_size": 3072,
    "layer_norm_eps": 1e-06,
    "model_type": "siglip_vision_model",
    "num_attention_heads": 12,
    "num_channels": 3,
    "num_hidden_layers": 12,
    "patch_size": 16,
    "torch_dtype": "float32"
  }
}