{ "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": 768, "id2label": { "0": "01", "1": "03", "2": "04", "3": "05", "4": "09", "5": "10", "6": "11", "7": "12", "8": "13", "9": "14", "10": "15", "11": "16", "12": "19", "13": "22", "14": "23", "15": "24", "16": "25", "17": "26", "18": "27", "19": "28", "20": "29", "21": "30", "22": "31", "23": "32", "24": "33", "25": "34", "26": "35", "27": "36", "28": "37", "29": "38", "30": "39", "31": "40", "32": "41", "33": "42", "34": "43", "35": "44", "36": "45", "37": "46", "38": "47", "39": "48", "40": "49", "41": "50", "42": "51", "43": "52", "44": "53", "45": "54", "46": "60", "47": "90" }, "initializer_cutoff_factor": 2.0, "initializer_range": 0.02, "intermediate_size": 1152, "label2id": { "01": 0, "03": 1, "04": 2, "05": 3, "09": 4, "10": 5, "11": 6, "12": 7, "13": 8, "14": 9, "15": 10, "16": 11, "19": 12, "22": 13, "23": 14, "24": 15, "25": 16, "26": 17, "27": 18, "28": 19, "29": 20, "30": 21, "31": 22, "32": 23, "33": 24, "34": 25, "35": 26, "36": 27, "37": 28, "38": 29, "39": 30, "40": 31, "41": 32, "42": 33, "43": 34, "44": 35, "45": 36, "46": 37, "47": 38, "48": 39, "49": 40, "50": 41, "51": 42, "52": 43, "53": 44, "54": 45, "60": 46, "90": 47 }, "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", "problem_type": "single_label_classification", "repad_logits_with_grad": false, "sep_token_id": 50282, "sparse_pred_ignore_index": -100, "sparse_prediction": false, "torch_dtype": "float32", "transformers_version": "4.51.3", "vocab_size": 50368 }