{ "_name_or_path": "./bert_arch_ner_bio_trained", "architectures": [ "ModernBertForTokenClassification" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 50281, "classifier_activation": "gelu", "classifier_bias": false, "classifier_dropout": 0.0, "classifier_pooling": "mean", "cls_token_id": 50281, "decoder_bias": true, "deterministic_flash_attn": false, "embedding_dropout": 0.0, "eos_token_id": 50282, "global_attn_every_n_layers": 3, "global_rope_theta": 160000.0, "gradient_checkpointing": false, "hidden_activation": "gelu", "hidden_size": 768, "id2label": { "0": "O", "1": "B-ORG", "2": "I-ORG", "3": "B-LOC", "4": "I-LOC", "5": "B-PER", "6": "I-PER", "7": "B-SUBJ", "8": "I-SUBJ", "9": "B-ID", "10": "I-ID" }, "initializer_cutoff_factor": 2.0, "initializer_range": 0.02, "intermediate_size": 1152, "label2id": { "B-ID": 9, "B-LOC": 3, "B-ORG": 1, "B-PER": 5, "B-SUBJ": 7, "I-ID": 10, "I-LOC": 4, "I-ORG": 2, "I-PER": 6, "I-SUBJ": 8, "O": 0 }, "layer_norm_eps": 1e-05, "local_attention": 128, "local_rope_theta": 10000.0, "max_position_embeddings": 8192, "mlp_bias": false, "mlp_dropout": 0.0, "model_type": "modernbert", "norm_bias": false, "norm_eps": 1e-05, "num_attention_heads": 12, "num_hidden_layers": 22, "pad_token_id": 50283, "position_embedding_type": "absolute", "reference_compile": false, "sep_token_id": 50282, "sparse_pred_ignore_index": -100, "sparse_prediction": false, "torch_dtype": "float32", "transformers_version": "4.48.0.dev0", "vocab_size": 50368 }