{ "add_cross_attention": false, "architectures": [ "RobertaForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "attention_window": [ 256, 256, 256, 256, 256, 256, 256, 256, 256, 256, 256, 256 ], "bos_token_id": 0, "classifier_dropout": null, "dtype": "float32", "eos_token_id": 2, "gradient_checkpointing": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "ai_noi_bo", "1": "bao_mat_du_lieu", "2": "cong_tac_chi_phi", "3": "email_thiet_bi", "4": "nghi_phep_remote" }, "initializer_range": 0.02, "intermediate_size": 3072, "is_decoder": false, "label2id": { "ai_noi_bo": 0, "bao_mat_du_lieu": 1, "cong_tac_chi_phi": 2, "email_thiet_bi": 3, "nghi_phep_remote": 4 }, "layer_norm_eps": 1e-05, "max_position_embeddings": 4098, "model_type": "roberta", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 1, "position_embedding_type": "absolute", "problem_type": "single_label_classification", "tie_word_embeddings": true, "tokenizer_class": "PhobertTokenizer", "transformers_version": "5.0.0", "type_vocab_size": 1, "use_cache": false, "vocab_size": 64001 }