{ "_name_or_path": "google/vit-base-patch16-224-in21k", "architectures": [ "ViTForImageClassification" ], "attention_probs_dropout_prob": 0.0, "encoder_stride": 16, "hidden_act": "gelu", "hidden_dropout_prob": 0.0, "hidden_size": 768, "id2label": { "0": "ain", "1": "aleff", "10": "haa", "11": "jeem", "12": "kaaf", "13": "khaa", "14": "laam", "15": "meem", "16": "nun", "17": "ra", "18": "saad", "19": "seen", "2": "bb", "20": "sheen", "21": "ta", "22": "taa", "23": "thaa", "24": "thal", "25": "waw", "26": "ya", "27": "zay", "3": "dal", "4": "dha", "5": "dhad", "6": "fa", "7": "gaaf", "8": "ghain", "9": "ha" }, "image_size": 224, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "ain": "0", "aleff": "1", "bb": "2", "dal": "3", "dha": "4", "dhad": "5", "fa": "6", "gaaf": "7", "ghain": "8", "ha": "9", "haa": "10", "jeem": "11", "kaaf": "12", "khaa": "13", "laam": "14", "meem": "15", "nun": "16", "ra": "17", "saad": "18", "seen": "19", "sheen": "20", "ta": "21", "taa": "22", "thaa": "23", "thal": "24", "waw": "25", "ya": "26", "zay": "27" }, "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": "4.41.2" }