{ "architectures": [ "SiglipForImageClassification" ], "id2label": { "0": "tench", "1": "goldfish", "2": "great white shark", "3": "tiger shark", "4": "hammerhead", "5": "electric ray", "6": "stingray", "7": "cock", "8": "hen", "9": "ostrich", "10": "brambling", "11": "goldfinch", "12": "house finch", "13": "junco", "14": "indigo bunting", "15": "robin", "16": "bulbul", "17": "jay", "18": "magpie", "19": "chickadee", "20": "water ouzel", "21": "kite", "22": "bald eagle", "23": "vulture", "24": "great grey owl", "25": "european fire salamander", "26": "common newt", "27": "eft", "28": "spotted salamander", "29": "axolotl", "30": "bullfrog", "31": "tree frog", "32": "tailed frog", "33": "loggerhead", "34": "leatherback turtle", "35": "mud turtle", "36": "terrapin", "37": "box turtle", "38": "banded gecko", "39": "common iguana", "40": "american chameleon", "41": "whiptail", "42": "agama", "43": "frilled lizard", "44": "alligator lizard", "45": "gila monster", "46": "green lizard", "47": "african chameleon", "48": "komodo dragon", "49": "african crocodile" }, "initializer_factor": 1.0, "label2id": { "african chameleon": 47, "african crocodile": 49, "agama": 42, "alligator lizard": 44, "american chameleon": 40, "axolotl": 29, "bald eagle": 22, "banded gecko": 38, "box turtle": 37, "brambling": 10, "bulbul": 16, "bullfrog": 30, "chickadee": 19, "cock": 7, "common iguana": 39, "common newt": 26, "eft": 27, "electric ray": 5, "european fire salamander": 25, "frilled lizard": 43, "gila monster": 45, "goldfinch": 11, "goldfish": 1, "great grey owl": 24, "great white shark": 2, "green lizard": 46, "hammerhead": 4, "hen": 8, "house finch": 12, "indigo bunting": 14, "jay": 17, "junco": 13, "kite": 21, "komodo dragon": 48, "leatherback turtle": 34, "loggerhead": 33, "magpie": 18, "mud turtle": 35, "ostrich": 9, "robin": 15, "spotted salamander": 28, "stingray": 6, "tailed frog": 32, "tench": 0, "terrapin": 36, "tiger shark": 3, "tree frog": 31, "vulture": 23, "water ouzel": 20, "whiptail": 41 }, "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": "4.50.0", "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" } }