| { | |
| "architectures": [ | |
| "SiglipForImageClassification" | |
| ], | |
| "id2label": { | |
| "0": "aircraft_carrier", | |
| "1": "alarm_clock", | |
| "2": "ant", | |
| "3": "anvil", | |
| "4": "asparagus", | |
| "5": "axe", | |
| "6": "banana", | |
| "7": "basket", | |
| "8": "bathtub", | |
| "9": "bear", | |
| "10": "bee", | |
| "11": "bird", | |
| "12": "blackberry", | |
| "13": "blueberry", | |
| "14": "bottlecap", | |
| "15": "broccoli", | |
| "16": "bus", | |
| "17": "butterfly", | |
| "18": "cactus", | |
| "19": "cake", | |
| "20": "calculator", | |
| "21": "camel", | |
| "22": "camera", | |
| "23": "candle", | |
| "24": "cannon", | |
| "25": "canoe", | |
| "26": "carrot", | |
| "27": "castle", | |
| "28": "cat", | |
| "29": "ceiling_fan", | |
| "30": "cell_phone", | |
| "31": "cello", | |
| "32": "chair", | |
| "33": "chandelier", | |
| "34": "coffee_cup", | |
| "35": "compass", | |
| "36": "computer", | |
| "37": "cow", | |
| "38": "crab", | |
| "39": "crocodile", | |
| "40": "cruise_ship", | |
| "41": "dog", | |
| "42": "dolphin", | |
| "43": "dragon", | |
| "44": "drums", | |
| "45": "duck", | |
| "46": "dumbbell", | |
| "47": "elephant", | |
| "48": "eyeglasses", | |
| "49": "feather", | |
| "50": "fence", | |
| "51": "fish", | |
| "52": "flamingo", | |
| "53": "flower", | |
| "54": "foot", | |
| "55": "fork", | |
| "56": "frog", | |
| "57": "giraffe", | |
| "58": "goatee", | |
| "59": "grapes", | |
| "60": "guitar", | |
| "61": "hammer", | |
| "62": "helicopter", | |
| "63": "helmet", | |
| "64": "horse", | |
| "65": "kangaroo", | |
| "66": "lantern", | |
| "67": "laptop", | |
| "68": "leaf", | |
| "69": "lion", | |
| "70": "lipstick", | |
| "71": "lobster", | |
| "72": "microphone", | |
| "73": "monkey", | |
| "74": "mosquito", | |
| "75": "mouse", | |
| "76": "mug", | |
| "77": "mushroom", | |
| "78": "onion", | |
| "79": "panda", | |
| "80": "peanut", | |
| "81": "pear", | |
| "82": "peas", | |
| "83": "pencil", | |
| "84": "penguin", | |
| "85": "pig", | |
| "86": "pillow", | |
| "87": "pineapple", | |
| "88": "potato", | |
| "89": "power_outlet", | |
| "90": "purse", | |
| "91": "rabbit", | |
| "92": "raccoon", | |
| "93": "rhinoceros", | |
| "94": "rifle", | |
| "95": "saxophone", | |
| "96": "screwdriver", | |
| "97": "sea_turtle", | |
| "98": "see_saw", | |
| "99": "sheep", | |
| "100": "shoe", | |
| "101": "skateboard", | |
| "102": "snake", | |
| "103": "speedboat", | |
| "104": "spider", | |
| "105": "squirrel", | |
| "106": "strawberry", | |
| "107": "streetlight", | |
| "108": "string_bean", | |
| "109": "submarine", | |
| "110": "swan", | |
| "111": "table", | |
| "112": "teapot", | |
| "113": "teddy-bear", | |
| "114": "television", | |
| "115": "the_Eiffel_Tower", | |
| "116": "the_Great_Wall_of_China", | |
| "117": "tiger", | |
| "118": "toe", | |
| "119": "train", | |
| "120": "truck", | |
| "121": "umbrella", | |
| "122": "vase", | |
| "123": "watermelon", | |
| "124": "whale", | |
| "125": "zebra" | |
| }, | |
| "initializer_factor": 1.0, | |
| "label2id": { | |
| "aircraft_carrier": 0, | |
| "alarm_clock": 1, | |
| "ant": 2, | |
| "anvil": 3, | |
| "asparagus": 4, | |
| "axe": 5, | |
| "banana": 6, | |
| "basket": 7, | |
| "bathtub": 8, | |
| "bear": 9, | |
| "bee": 10, | |
| "bird": 11, | |
| "blackberry": 12, | |
| "blueberry": 13, | |
| "bottlecap": 14, | |
| "broccoli": 15, | |
| "bus": 16, | |
| "butterfly": 17, | |
| "cactus": 18, | |
| "cake": 19, | |
| "calculator": 20, | |
| "camel": 21, | |
| "camera": 22, | |
| "candle": 23, | |
| "cannon": 24, | |
| "canoe": 25, | |
| "carrot": 26, | |
| "castle": 27, | |
| "cat": 28, | |
| "ceiling_fan": 29, | |
| "cell_phone": 30, | |
| "cello": 31, | |
| "chair": 32, | |
| "chandelier": 33, | |
| "coffee_cup": 34, | |
| "compass": 35, | |
| "computer": 36, | |
| "cow": 37, | |
| "crab": 38, | |
| "crocodile": 39, | |
| "cruise_ship": 40, | |
| "dog": 41, | |
| "dolphin": 42, | |
| "dragon": 43, | |
| "drums": 44, | |
| "duck": 45, | |
| "dumbbell": 46, | |
| "elephant": 47, | |
| "eyeglasses": 48, | |
| "feather": 49, | |
| "fence": 50, | |
| "fish": 51, | |
| "flamingo": 52, | |
| "flower": 53, | |
| "foot": 54, | |
| "fork": 55, | |
| "frog": 56, | |
| "giraffe": 57, | |
| "goatee": 58, | |
| "grapes": 59, | |
| "guitar": 60, | |
| "hammer": 61, | |
| "helicopter": 62, | |
| "helmet": 63, | |
| "horse": 64, | |
| "kangaroo": 65, | |
| "lantern": 66, | |
| "laptop": 67, | |
| "leaf": 68, | |
| "lion": 69, | |
| "lipstick": 70, | |
| "lobster": 71, | |
| "microphone": 72, | |
| "monkey": 73, | |
| "mosquito": 74, | |
| "mouse": 75, | |
| "mug": 76, | |
| "mushroom": 77, | |
| "onion": 78, | |
| "panda": 79, | |
| "peanut": 80, | |
| "pear": 81, | |
| "peas": 82, | |
| "pencil": 83, | |
| "penguin": 84, | |
| "pig": 85, | |
| "pillow": 86, | |
| "pineapple": 87, | |
| "potato": 88, | |
| "power_outlet": 89, | |
| "purse": 90, | |
| "rabbit": 91, | |
| "raccoon": 92, | |
| "rhinoceros": 93, | |
| "rifle": 94, | |
| "saxophone": 95, | |
| "screwdriver": 96, | |
| "sea_turtle": 97, | |
| "see_saw": 98, | |
| "sheep": 99, | |
| "shoe": 100, | |
| "skateboard": 101, | |
| "snake": 102, | |
| "speedboat": 103, | |
| "spider": 104, | |
| "squirrel": 105, | |
| "strawberry": 106, | |
| "streetlight": 107, | |
| "string_bean": 108, | |
| "submarine": 109, | |
| "swan": 110, | |
| "table": 111, | |
| "teapot": 112, | |
| "teddy-bear": 113, | |
| "television": 114, | |
| "the_Eiffel_Tower": 115, | |
| "the_Great_Wall_of_China": 116, | |
| "tiger": 117, | |
| "toe": 118, | |
| "train": 119, | |
| "truck": 120, | |
| "umbrella": 121, | |
| "vase": 122, | |
| "watermelon": 123, | |
| "whale": 124, | |
| "zebra": 125 | |
| }, | |
| "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" | |
| } | |
| } | |