{ "architectures": [ "SiglipForImageClassification" ], "id2label": { "0": "\u090b", "1": "\u0915", "2": "\u0916", "3": "\u0917", "4": "\u0918", "5": "\u0919", "6": "\u091a", "7": "\u091b", "8": "\u091c", "9": "\u091d", "10": "\u091f", "11": "\u0920", "12": "\u0922", "13": "\u0923", "14": "\u0924", "15": "\u0925", "16": "\u0926", "17": "\u0928", "18": "\u092a", "19": "\u092b", "20": "\u092c", "21": "\u092d", "22": "\u092e", "23": "\u092f", "24": "\u0930", "25": "\u0932", "26": "\u0935", "27": "\u0938", "28": "\u0939" }, "initializer_factor": 1.0, "label2id": { "\u090b": 0, "\u0915": 1, "\u0916": 2, "\u0917": 3, "\u0918": 4, "\u0919": 5, "\u091a": 6, "\u091b": 7, "\u091c": 8, "\u091d": 9, "\u091f": 10, "\u0920": 11, "\u0922": 12, "\u0923": 13, "\u0924": 14, "\u0925": 15, "\u0926": 16, "\u0928": 17, "\u092a": 18, "\u092b": 19, "\u092c": 20, "\u092d": 21, "\u092e": 22, "\u092f": 23, "\u0930": 24, "\u0932": 25, "\u0935": 26, "\u0938": 27, "\u0939": 28 }, "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" } }