{ "_name_or_path": "bert-base-uncased", "architectures": [ "BertForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "nso", "1": "tsn", "10": "eng", "2": "sot", "3": "ven", "4": "af", "5": "tso", "6": "ssw", "7": "zul", "8": "xho", "9": "nbl" }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "af": 4, "eng": 10, "nbl": 9, "nso": 0, "sot": 2, "ssw": 6, "tsn": 1, "tso": 5, "ven": 3, "xho": 8, "zul": 7 }, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 0, "position_embedding_type": "absolute", "problem_type": "single_label_classification", "torch_dtype": "float32", "transformers_version": "4.41.2", "type_vocab_size": 2, "use_cache": true, "vocab_size": 30522 }