{ "_name_or_path": "bert-base-multilingual-cased", "architectures": [ "BertForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "directionality": "bidi", "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "ar", "1": "bg", "2": "de", "3": "el", "4": "en", "5": "es", "6": "fr", "7": "hi", "8": "it", "9": "ja", "10": "nl", "11": "pl", "12": "pt", "13": "ru", "14": "sw", "15": "th", "16": "tr", "17": "ur", "18": "vi", "19": "zh" }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "ar": 0, "bg": 1, "de": 2, "el": 3, "en": 4, "es": 5, "fr": 6, "hi": 7, "it": 8, "ja": 9, "nl": 10, "pl": 11, "pt": 12, "ru": 13, "sw": 14, "th": 15, "tr": 16, "ur": 17, "vi": 18, "zh": 19 }, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 0, "pooler_fc_size": 768, "pooler_num_attention_heads": 12, "pooler_num_fc_layers": 3, "pooler_size_per_head": 128, "pooler_type": "first_token_transform", "position_embedding_type": "absolute", "problem_type": "single_label_classification", "torch_dtype": "float32", "transformers_version": "4.35.2", "type_vocab_size": 2, "use_cache": true, "vocab_size": 119547 }