config.json

{
  "architectures": [
    "ModernBertForTokenClassification"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "auto_map": {
    "AutoConfig": "configuration_modernbert.ModernBertConfig",
    "AutoModel": "modeling_modernbert.ModernBertModel",
    "AutoModelForMaskedLM": "modeling_modernbert.ModernBertForMaskedLM",
    "AutoModelForSequenceClassification": "modeling_modernbert.ModernBertForSequenceClassification",
    "AutoModelForTokenClassification": "modeling_modernbert.ModernBertForTokenClassification"
  },
  "bos_token_id": 0,
  "classifier_activation": "gelu",
  "classifier_bias": false,
  "classifier_dropout": 0.0,
  "classifier_pooling": "mean",
  "cls_token_id": 0,
  "custom_pipelines": {
    "upos": {
      "impl": "upos.BellmanFordTokenClassificationPipeline",
      "pt": "AutoModelForTokenClassification"
    }
  },
  "decoder_bias": true,
  "deterministic_flash_attn": false,
  "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": 1024,
  "id2label": {
    "0": "ADJ",
    "1": "ADP",
    "2": "ADV",
    "3": "AUX",
    "4": "AUX|Polarity=Neg",
    "5": "B-ADJ",
    "6": "B-ADP",
    "7": "B-ADV",
    "8": "B-AUX",
    "9": "B-AUX|Polarity=Neg",
    "10": "B-CCONJ",
    "11": "B-DET",
    "12": "B-INTJ",
    "13": "B-NOUN",
    "14": "B-NOUN|Polarity=Neg",
    "15": "B-NUM",
    "16": "B-PART",
    "17": "B-PRON",
    "18": "B-PROPN",
    "19": "B-PUNCT",
    "20": "B-SCONJ",
    "21": "B-SYM",
    "22": "B-VERB",
    "23": "B-X",
    "24": "CCONJ",
    "25": "DET",
    "26": "I-ADJ",
    "27": "I-ADP",
    "28": "I-ADV",
    "29": "I-AUX",
    "30": "I-AUX|Polarity=Neg",
    "31": "I-CCONJ",
    "32": "I-DET",
    "33": "I-INTJ",
    "34": "I-NOUN",
    "35": "I-NOUN|Polarity=Neg",
    "36": "I-NUM",
    "37": "I-PART",
    "38": "I-PRON",
    "39": "I-PROPN",
    "40": "I-PUNCT",
    "41": "I-SCONJ",
    "42": "I-SYM",
    "43": "I-VERB",
    "44": "I-X",
    "45": "INTJ",
    "46": "NOUN",
    "47": "NUM",
    "48": "PART",
    "49": "PRON",
    "50": "PROPN",
    "51": "PUNCT",
    "52": "SCONJ",
    "53": "SYM",
    "54": "VERB",
    "55": "X"
  },
  "initializer_cutoff_factor": 2.0,
  "initializer_range": 0.02,
  "intermediate_size": 2624,
  "label2id": {
    "ADJ": 0,
    "ADP": 1,
    "ADV": 2,
    "AUX": 3,
    "AUX|Polarity=Neg": 4,
    "B-ADJ": 5,
    "B-ADP": 6,
    "B-ADV": 7,
    "B-AUX": 8,
    "B-AUX|Polarity=Neg": 9,
    "B-CCONJ": 10,
    "B-DET": 11,
    "B-INTJ": 12,
    "B-NOUN": 13,
    "B-NOUN|Polarity=Neg": 14,
    "B-NUM": 15,
    "B-PART": 16,
    "B-PRON": 17,
    "B-PROPN": 18,
    "B-PUNCT": 19,
    "B-SCONJ": 20,
    "B-SYM": 21,
    "B-VERB": 22,
    "B-X": 23,
    "CCONJ": 24,
    "DET": 25,
    "I-ADJ": 26,
    "I-ADP": 27,
    "I-ADV": 28,
    "I-AUX": 29,
    "I-AUX|Polarity=Neg": 30,
    "I-CCONJ": 31,
    "I-DET": 32,
    "I-INTJ": 33,
    "I-NOUN": 34,
    "I-NOUN|Polarity=Neg": 35,
    "I-NUM": 36,
    "I-PART": 37,
    "I-PRON": 38,
    "I-PROPN": 39,
    "I-PUNCT": 40,
    "I-SCONJ": 41,
    "I-SYM": 42,
    "I-VERB": 43,
    "I-X": 44,
    "INTJ": 45,
    "NOUN": 46,
    "NUM": 47,
    "PART": 48,
    "PRON": 49,
    "PROPN": 50,
    "PUNCT": 51,
    "SCONJ": 52,
    "SYM": 53,
    "VERB": 54,
    "X": 55
  },
  "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": 1,
  "position_embedding_type": "absolute",
  "reference_compile": true,
  "repad_logits_with_grad": false,
  "sep_token_id": 2,
  "sparse_pred_ignore_index": -100,
  "sparse_prediction": false,
  "tokenizer_class": "DebertaV2TokenizerFast",
  "torch_dtype": "float32",
  "transformers_version": "4.48.0",
  "vocab_size": 65000
}