{ "architectures": [ "ModernBertForSequenceClassification" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "classifier_activation": "gelu", "classifier_bias": false, "classifier_dropout": 0.0, "classifier_pooling": "cls", "cls_token_id": 6, "decoder_bias": true, "deterministic_flash_attn": false, "dtype": "float32", "embedding_dropout": 0.0, "eos_token_id": 2, "global_attn_every_n_layers": 3, "global_rope_theta": 160000.0, "gradient_checkpointing": false, "hidden_activation": "gelu", "hidden_size": 768, "id2label": { "0": "apartment", "1": "outdoor", "2": "highway", "3": "inside_train", "4": "station", "5": "commercial_facility", "6": "river" }, "initializer_cutoff_factor": 2.0, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "apartment": 0, "commercial_facility": 5, "highway": 2, "inside_train": 3, "outdoor": 1, "river": 6, "station": 4 }, "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": 25, "pad_token_id": 3, "position_embedding_type": "rope", "problem_type": "multi_label_classification", "repad_logits_with_grad": false, "sep_token_id": 4, "sparse_pred_ignore_index": -100, "sparse_prediction": false, "transformers_version": "4.56.2", "vocab_size": 102400 }