{ "architectures": [ "ModernBertForSequenceClassification" ], "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": 1024, "id2label": { "0": "0-10", "1": "1001\u20132000", "2": "101\u2013150", "3": "11-20", "4": "151\u2013200", "5": "2001\u20135000", "6": "201\u2013250", "7": "21-40", "8": "251\u2013500", "9": "41-60", "10": "5001\u201310000", "11": "501\u20131000", "12": "61\u2013100" }, "initializer_cutoff_factor": 2.0, "initializer_range": 0.02, "intermediate_size": 2624, "label2id": { "0-10": 0, "1001\u20132000": 1, "101\u2013150": 2, "11-20": 3, "151\u2013200": 4, "2001\u20135000": 5, "201\u2013250": 6, "21-40": 7, "251\u2013500": 8, "41-60": 9, "5001\u201310000": 10, "501\u20131000": 11, "61\u2013100": 12 }, "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": 16, "num_hidden_layers": 28, "pad_token_id": 50283, "position_embedding_type": "absolute", "problem_type": "single_label_classification", "repad_logits_with_grad": false, "sep_token_id": 50282, "sparse_pred_ignore_index": -100, "sparse_prediction": false, "torch_dtype": "bfloat16", "transformers_version": "4.55.4", "unsloth_version": "2025.9.4", "vocab_size": 50368 }