| { | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "BertForSequenceClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": null, | |
| "classifier_dropout": null, | |
| "dtype": "float32", | |
| "eos_token_id": null, | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "OM", | |
| "1": "SD", | |
| "2": "SA", | |
| "3": "KW", | |
| "4": "QA", | |
| "5": "LB", | |
| "6": "JO", | |
| "7": "SY", | |
| "8": "IQ", | |
| "9": "MA", | |
| "10": "EG", | |
| "11": "PL", | |
| "12": "YE", | |
| "13": "BH", | |
| "14": "DZ", | |
| "15": "AE", | |
| "16": "TN", | |
| "17": "LY" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "is_decoder": false, | |
| "label2id": { | |
| "AE": 15, | |
| "BH": 13, | |
| "DZ": 14, | |
| "EG": 10, | |
| "IQ": 8, | |
| "JO": 6, | |
| "KW": 3, | |
| "LB": 5, | |
| "LY": 17, | |
| "MA": 9, | |
| "OM": 0, | |
| "PL": 11, | |
| "QA": 4, | |
| "SA": 2, | |
| "SD": 1, | |
| "SY": 7, | |
| "TN": 16, | |
| "YE": 12 | |
| }, | |
| "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", | |
| "tie_word_embeddings": true, | |
| "transformers_version": "5.18.0", | |
| "type_vocab_size": 2, | |
| "use_cache": false, | |
| "vocab_size": 64000 | |
| } | |