{ "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": 768, "id2label": { "0": "ADP", "1": "ADP|Foreign=Yes", "2": "ADP|NounType=Class", "3": "ADP|Prefix=Yes", "4": "ADV", "5": "ADV|Foreign=Yes", "6": "ADV|NumType=Mult", "7": "ADV|PartType=Adv", "8": "ADV|PartType=Enp", "9": "ADV|PartType=Int", "10": "ADV|Prefix=Yes", "11": "AUX", "12": "AUX|Prefix=Yes", "13": "AUX|VerbType=Cop", "14": "B-ADP", "15": "B-ADV", "16": "B-ADV|NumType=Mult", "17": "B-ADV|PartType=Adv", "18": "B-ADV|PartType=Enp", "19": "B-ADV|PronType=Int", "20": "B-AUX", "21": "B-AUX|NounType=Class", "22": "B-AUX|VerbType=Cop", "23": "B-CCONJ", "24": "B-CCONJ|PronType=Prs", "25": "B-DET", "26": "B-DET|PartType=Int", "27": "B-INTJ", "28": "B-NOUN", "29": "B-NOUN|Abbr=Yes", "30": "B-NOUN|Abbr=Yes|Foreign=Yes", "31": "B-NOUN|Abbr=Yes|Prefix=Yes", "32": "B-NOUN|Foreign=Yes", "33": "B-NOUN|Foreign=Yes|NounType=Class", "34": "B-NOUN|Foreign=Yes|Prefix=Yes", "35": "B-NOUN|NameType=Com", "36": "B-NOUN|NameType=Geo", "37": "B-NOUN|NameType=Oth", "38": "B-NOUN|NameType=Prs", "39": "B-NOUN|NounType=Class", "40": "B-NOUN|NounType=Class|Prefix=Yes", "41": "B-NOUN|NumType=Mult", "42": "B-NOUN|Prefix=Yes", "43": "B-NUM", "44": "B-NUM|Abbr=Yes", "45": "B-NUM|Foreign=Yes", "46": "B-NUM|NumType=Mult", "47": "B-PART", "48": "B-PART|Aspect=Perf", "49": "B-PART|Aspect=Prog", "50": "B-PART|NounType=Class|PartType=Emp", "51": "B-PART|NounType=Class|PartType=Emp|Prefix=Yes", "52": "B-PART|NounType=Class|Prefix=Yes", "53": "B-PART|NumType=Mult|PartType=Emp", "54": "B-PART|PartType=Adj", "55": "B-PART|PartType=Adv", "56": "B-PART|PartType=Emp", "57": "B-PART|PartType=Emp|Prefix=Yes", "58": "B-PART|PartType=Enp", "59": "B-PART|PartType=Int", "60": "B-PART|PartType=Neg", "61": "B-PART|Polarity=Neg", "62": "B-PART|Prefix=Yes", "63": "B-PART|PronType=Int", "64": "B-PRON", "65": "B-PRON|Person=1", "66": "B-PRON|Person=2", "67": "B-PRON|Person=3", "68": "B-PRON|PronType=Prs", "69": "B-PRON|PronType=Rcp", "70": "B-PROPN", "71": "B-PROPN|Abbr=Yes", "72": "B-PROPN|Abbr=Yes|Foreign=Yes|NameType=Oth", "73": "B-PROPN|Foreign=Yes", "74": "B-PROPN|Foreign=Yes|NameType=Com", "75": "B-PROPN|Foreign=Yes|NameType=Geo", "76": "B-PROPN|Foreign=Yes|NameType=Giv", "77": "B-PROPN|Foreign=Yes|NameType=Oth", "78": "B-PROPN|Foreign=Yes|NameType=Prs", "79": "B-PROPN|Foreign=Yes|NameType=Sur", "80": "B-PROPN|NameType=Com", "81": "B-PROPN|NameType=Geo", "82": "B-PROPN|NameType=Giv", "83": "B-PROPN|NameType=Nat", "84": "B-PROPN|NameType=Oth", "85": "B-PROPN|NameType=Pro", "86": "B-PROPN|NameType=Prs", "87": "B-PROPN|NameType=Sur", "88": "B-PUNCT", "89": "B-SCONJ", "90": "B-VERB", "91": "B-VERB|Foreign=Yes", "92": "B-VERB|PartType=Adj", "93": "B-VERB|Prefix=Yes", "94": "B-VERB|VerbType=Cop", "95": "B-VERB|Voice=Pass", "96": "B-X", "97": "CCONJ", "98": "DET", "99": "DET|PartType=Emp", "100": "DET|PronType=Int", "101": "I-ADP", "102": "I-ADV", "103": "I-ADV|NumType=Mult", "104": "I-ADV|PartType=Adv", "105": "I-ADV|PartType=Enp", "106": "I-ADV|PronType=Int", "107": "I-AUX", "108": "I-AUX|NounType=Class", "109": "I-AUX|VerbType=Cop", "110": "I-CCONJ", "111": "I-CCONJ|PronType=Prs", "112": "I-DET", "113": "I-DET|PartType=Int", "114": "I-INTJ", "115": "I-NOUN", "116": "I-NOUN|Abbr=Yes", "117": "I-NOUN|Abbr=Yes|Foreign=Yes", "118": "I-NOUN|Abbr=Yes|Prefix=Yes", "119": "I-NOUN|Foreign=Yes", "120": "I-NOUN|Foreign=Yes|NounType=Class", "121": "I-NOUN|Foreign=Yes|Prefix=Yes", "122": "I-NOUN|NameType=Com", "123": "I-NOUN|NameType=Geo", "124": "I-NOUN|NameType=Oth", "125": "I-NOUN|NameType=Prs", "126": "I-NOUN|NounType=Class", "127": "I-NOUN|NounType=Class|Prefix=Yes", "128": "I-NOUN|NumType=Mult", "129": "I-NOUN|Prefix=Yes", "130": "I-NUM", "131": "I-NUM|Abbr=Yes", "132": "I-NUM|Foreign=Yes", "133": "I-NUM|NumType=Mult", "134": "I-PART", "135": "I-PART|Aspect=Perf", "136": "I-PART|Aspect=Prog", "137": "I-PART|NounType=Class|PartType=Emp", "138": "I-PART|NounType=Class|PartType=Emp|Prefix=Yes", "139": "I-PART|NounType=Class|Prefix=Yes", "140": "I-PART|NumType=Mult|PartType=Emp", "141": "I-PART|PartType=Adj", "142": "I-PART|PartType=Adv", "143": "I-PART|PartType=Emp", "144": "I-PART|PartType=Emp|Prefix=Yes", "145": "I-PART|PartType=Enp", "146": "I-PART|PartType=Int", "147": "I-PART|PartType=Neg", "148": "I-PART|Polarity=Neg", "149": "I-PART|Prefix=Yes", "150": "I-PART|PronType=Int", "151": "I-PRON", "152": "I-PRON|Person=1", "153": "I-PRON|Person=2", "154": "I-PRON|Person=3", "155": "I-PRON|PronType=Prs", "156": "I-PRON|PronType=Rcp", "157": "I-PROPN", "158": "I-PROPN|Abbr=Yes", "159": "I-PROPN|Abbr=Yes|Foreign=Yes|NameType=Oth", "160": "I-PROPN|Foreign=Yes", "161": "I-PROPN|Foreign=Yes|NameType=Com", "162": "I-PROPN|Foreign=Yes|NameType=Geo", "163": "I-PROPN|Foreign=Yes|NameType=Giv", "164": "I-PROPN|Foreign=Yes|NameType=Oth", "165": "I-PROPN|Foreign=Yes|NameType=Prs", "166": "I-PROPN|Foreign=Yes|NameType=Sur", "167": "I-PROPN|NameType=Com", "168": "I-PROPN|NameType=Geo", "169": "I-PROPN|NameType=Giv", "170": "I-PROPN|NameType=Nat", "171": "I-PROPN|NameType=Oth", "172": "I-PROPN|NameType=Pro", "173": "I-PROPN|NameType=Prs", "174": "I-PROPN|NameType=Sur", "175": "I-PUNCT", "176": "I-SCONJ", "177": "I-VERB", "178": "I-VERB|Foreign=Yes", "179": "I-VERB|PartType=Adj", "180": "I-VERB|Prefix=Yes", "181": "I-VERB|VerbType=Cop", "182": "I-VERB|Voice=Pass", "183": "I-X", "184": "INTJ", "185": "NOUN", "186": "NOUN|Foreign=Yes", "187": "NOUN|NameType=Oth", "188": "NOUN|NounType=Class", "189": "NOUN|PartType=Enp", "190": "NOUN|PartType=Int", "191": "NOUN|PartType=Res", "192": "NOUN|Prefix=Yes", "193": "NUM", "194": "NUM|NumType=Mult", "195": "NUM|Prefix=Yes", "196": "PART", "197": "PART|Aspect=Perf", "198": "PART|Aspect=Prog", "199": "PART|NameType=Oth", "200": "PART|PartType=Adj", "201": "PART|PartType=Adv", "202": "PART|PartType=Emp", "203": "PART|PartType=Enp", "204": "PART|PartType=Int", "205": "PART|PartType=Neg", "206": "PART|PartType=Res", "207": "PART|Polarity=Neg", "208": "PART|Prefix=Yes", "209": "PART|PronType=Int", "210": "PRON", "211": "PRON|NounType=Class", "212": "PRON|Person=1", "213": "PRON|Person=2", "214": "PRON|Person=3", "215": "PRON|PronType=Int", "216": "PRON|PronType=Prs", "217": "PRON|PronType=Rcp", "218": "PROPN", "219": "PROPN|Foreign=Yes", "220": "PROPN|Foreign=Yes|NameType=Prs", "221": "PROPN|NameType=Com", "222": "PROPN|NameType=Geo", "223": "PROPN|NameType=Giv", "224": "PROPN|NameType=Nat", "225": "PROPN|NameType=Oth", "226": "PROPN|NameType=Pro", "227": "PROPN|NameType=Prs", "228": "PROPN|NounType=Class", "229": "PUNCT", "230": "PUNCT|NounType=Class", "231": "SCONJ", "232": "SCONJ|Prefix=Yes", "233": "SCONJ|VerbType=Cop", "234": "SYM", "235": "VERB", "236": "VERB|Foreign=Yes", "237": "VERB|Mood=Imp", "238": "VERB|NounType=Class", "239": "VERB|Prefix=Yes", "240": "VERB|VerbType=Cop", "241": "VERB|Voice=Pass", "242": "X" }, "initializer_cutoff_factor": 2.0, "initializer_range": 0.02, "intermediate_size": 1152, "label2id": { "ADP": 0, "ADP|Foreign=Yes": 1, "ADP|NounType=Class": 2, "ADP|Prefix=Yes": 3, "ADV": 4, "ADV|Foreign=Yes": 5, "ADV|NumType=Mult": 6, "ADV|PartType=Adv": 7, "ADV|PartType=Enp": 8, "ADV|PartType=Int": 9, "ADV|Prefix=Yes": 10, "AUX": 11, "AUX|Prefix=Yes": 12, "AUX|VerbType=Cop": 13, "B-ADP": 14, "B-ADV": 15, "B-ADV|NumType=Mult": 16, "B-ADV|PartType=Adv": 17, "B-ADV|PartType=Enp": 18, "B-ADV|PronType=Int": 19, "B-AUX": 20, "B-AUX|NounType=Class": 21, "B-AUX|VerbType=Cop": 22, "B-CCONJ": 23, "B-CCONJ|PronType=Prs": 24, "B-DET": 25, "B-DET|PartType=Int": 26, "B-INTJ": 27, "B-NOUN": 28, "B-NOUN|Abbr=Yes": 29, "B-NOUN|Abbr=Yes|Foreign=Yes": 30, "B-NOUN|Abbr=Yes|Prefix=Yes": 31, "B-NOUN|Foreign=Yes": 32, "B-NOUN|Foreign=Yes|NounType=Class": 33, "B-NOUN|Foreign=Yes|Prefix=Yes": 34, "B-NOUN|NameType=Com": 35, "B-NOUN|NameType=Geo": 36, "B-NOUN|NameType=Oth": 37, "B-NOUN|NameType=Prs": 38, "B-NOUN|NounType=Class": 39, "B-NOUN|NounType=Class|Prefix=Yes": 40, "B-NOUN|NumType=Mult": 41, "B-NOUN|Prefix=Yes": 42, "B-NUM": 43, "B-NUM|Abbr=Yes": 44, "B-NUM|Foreign=Yes": 45, "B-NUM|NumType=Mult": 46, "B-PART": 47, "B-PART|Aspect=Perf": 48, "B-PART|Aspect=Prog": 49, "B-PART|NounType=Class|PartType=Emp": 50, "B-PART|NounType=Class|PartType=Emp|Prefix=Yes": 51, "B-PART|NounType=Class|Prefix=Yes": 52, "B-PART|NumType=Mult|PartType=Emp": 53, "B-PART|PartType=Adj": 54, "B-PART|PartType=Adv": 55, "B-PART|PartType=Emp": 56, "B-PART|PartType=Emp|Prefix=Yes": 57, "B-PART|PartType=Enp": 58, "B-PART|PartType=Int": 59, "B-PART|PartType=Neg": 60, "B-PART|Polarity=Neg": 61, "B-PART|Prefix=Yes": 62, "B-PART|PronType=Int": 63, "B-PRON": 64, "B-PRON|Person=1": 65, "B-PRON|Person=2": 66, "B-PRON|Person=3": 67, "B-PRON|PronType=Prs": 68, "B-PRON|PronType=Rcp": 69, "B-PROPN": 70, "B-PROPN|Abbr=Yes": 71, "B-PROPN|Abbr=Yes|Foreign=Yes|NameType=Oth": 72, "B-PROPN|Foreign=Yes": 73, "B-PROPN|Foreign=Yes|NameType=Com": 74, "B-PROPN|Foreign=Yes|NameType=Geo": 75, "B-PROPN|Foreign=Yes|NameType=Giv": 76, "B-PROPN|Foreign=Yes|NameType=Oth": 77, "B-PROPN|Foreign=Yes|NameType=Prs": 78, "B-PROPN|Foreign=Yes|NameType=Sur": 79, "B-PROPN|NameType=Com": 80, "B-PROPN|NameType=Geo": 81, "B-PROPN|NameType=Giv": 82, "B-PROPN|NameType=Nat": 83, "B-PROPN|NameType=Oth": 84, "B-PROPN|NameType=Pro": 85, "B-PROPN|NameType=Prs": 86, "B-PROPN|NameType=Sur": 87, "B-PUNCT": 88, "B-SCONJ": 89, "B-VERB": 90, "B-VERB|Foreign=Yes": 91, "B-VERB|PartType=Adj": 92, "B-VERB|Prefix=Yes": 93, "B-VERB|VerbType=Cop": 94, "B-VERB|Voice=Pass": 95, "B-X": 96, "CCONJ": 97, "DET": 98, "DET|PartType=Emp": 99, "DET|PronType=Int": 100, "I-ADP": 101, "I-ADV": 102, "I-ADV|NumType=Mult": 103, "I-ADV|PartType=Adv": 104, "I-ADV|PartType=Enp": 105, "I-ADV|PronType=Int": 106, "I-AUX": 107, "I-AUX|NounType=Class": 108, "I-AUX|VerbType=Cop": 109, "I-CCONJ": 110, "I-CCONJ|PronType=Prs": 111, "I-DET": 112, "I-DET|PartType=Int": 113, "I-INTJ": 114, "I-NOUN": 115, "I-NOUN|Abbr=Yes": 116, "I-NOUN|Abbr=Yes|Foreign=Yes": 117, "I-NOUN|Abbr=Yes|Prefix=Yes": 118, "I-NOUN|Foreign=Yes": 119, "I-NOUN|Foreign=Yes|NounType=Class": 120, "I-NOUN|Foreign=Yes|Prefix=Yes": 121, "I-NOUN|NameType=Com": 122, "I-NOUN|NameType=Geo": 123, "I-NOUN|NameType=Oth": 124, "I-NOUN|NameType=Prs": 125, "I-NOUN|NounType=Class": 126, "I-NOUN|NounType=Class|Prefix=Yes": 127, "I-NOUN|NumType=Mult": 128, "I-NOUN|Prefix=Yes": 129, "I-NUM": 130, "I-NUM|Abbr=Yes": 131, "I-NUM|Foreign=Yes": 132, "I-NUM|NumType=Mult": 133, "I-PART": 134, "I-PART|Aspect=Perf": 135, "I-PART|Aspect=Prog": 136, "I-PART|NounType=Class|PartType=Emp": 137, "I-PART|NounType=Class|PartType=Emp|Prefix=Yes": 138, "I-PART|NounType=Class|Prefix=Yes": 139, "I-PART|NumType=Mult|PartType=Emp": 140, "I-PART|PartType=Adj": 141, "I-PART|PartType=Adv": 142, "I-PART|PartType=Emp": 143, "I-PART|PartType=Emp|Prefix=Yes": 144, "I-PART|PartType=Enp": 145, "I-PART|PartType=Int": 146, "I-PART|PartType=Neg": 147, "I-PART|Polarity=Neg": 148, "I-PART|Prefix=Yes": 149, "I-PART|PronType=Int": 150, "I-PRON": 151, "I-PRON|Person=1": 152, "I-PRON|Person=2": 153, "I-PRON|Person=3": 154, "I-PRON|PronType=Prs": 155, "I-PRON|PronType=Rcp": 156, "I-PROPN": 157, "I-PROPN|Abbr=Yes": 158, "I-PROPN|Abbr=Yes|Foreign=Yes|NameType=Oth": 159, "I-PROPN|Foreign=Yes": 160, "I-PROPN|Foreign=Yes|NameType=Com": 161, "I-PROPN|Foreign=Yes|NameType=Geo": 162, "I-PROPN|Foreign=Yes|NameType=Giv": 163, "I-PROPN|Foreign=Yes|NameType=Oth": 164, "I-PROPN|Foreign=Yes|NameType=Prs": 165, "I-PROPN|Foreign=Yes|NameType=Sur": 166, "I-PROPN|NameType=Com": 167, "I-PROPN|NameType=Geo": 168, "I-PROPN|NameType=Giv": 169, "I-PROPN|NameType=Nat": 170, "I-PROPN|NameType=Oth": 171, "I-PROPN|NameType=Pro": 172, "I-PROPN|NameType=Prs": 173, "I-PROPN|NameType=Sur": 174, "I-PUNCT": 175, "I-SCONJ": 176, "I-VERB": 177, "I-VERB|Foreign=Yes": 178, "I-VERB|PartType=Adj": 179, "I-VERB|Prefix=Yes": 180, "I-VERB|VerbType=Cop": 181, "I-VERB|Voice=Pass": 182, "I-X": 183, "INTJ": 184, "NOUN": 185, "NOUN|Foreign=Yes": 186, "NOUN|NameType=Oth": 187, "NOUN|NounType=Class": 188, "NOUN|PartType=Enp": 189, "NOUN|PartType=Int": 190, "NOUN|PartType=Res": 191, "NOUN|Prefix=Yes": 192, "NUM": 193, "NUM|NumType=Mult": 194, "NUM|Prefix=Yes": 195, "PART": 196, "PART|Aspect=Perf": 197, "PART|Aspect=Prog": 198, "PART|NameType=Oth": 199, "PART|PartType=Adj": 200, "PART|PartType=Adv": 201, "PART|PartType=Emp": 202, "PART|PartType=Enp": 203, "PART|PartType=Int": 204, "PART|PartType=Neg": 205, "PART|PartType=Res": 206, "PART|Polarity=Neg": 207, "PART|Prefix=Yes": 208, "PART|PronType=Int": 209, "PRON": 210, "PRON|NounType=Class": 211, "PRON|Person=1": 212, "PRON|Person=2": 213, "PRON|Person=3": 214, "PRON|PronType=Int": 215, "PRON|PronType=Prs": 216, "PRON|PronType=Rcp": 217, "PROPN": 218, "PROPN|Foreign=Yes": 219, "PROPN|Foreign=Yes|NameType=Prs": 220, "PROPN|NameType=Com": 221, "PROPN|NameType=Geo": 222, "PROPN|NameType=Giv": 223, "PROPN|NameType=Nat": 224, "PROPN|NameType=Oth": 225, "PROPN|NameType=Pro": 226, "PROPN|NameType=Prs": 227, "PROPN|NounType=Class": 228, "PUNCT": 229, "PUNCT|NounType=Class": 230, "SCONJ": 231, "SCONJ|Prefix=Yes": 232, "SCONJ|VerbType=Cop": 233, "SYM": 234, "VERB": 235, "VERB|Foreign=Yes": 236, "VERB|Mood=Imp": 237, "VERB|NounType=Class": 238, "VERB|Prefix=Yes": 239, "VERB|VerbType=Cop": 240, "VERB|Voice=Pass": 241, "X": 242 }, "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": 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, "task_specific_params": { "esupar_lemmatize": "copy" }, "tokenizer_class": "DebertaV2TokenizerFast", "torch_dtype": "float32", "transformers_version": "4.48.0", "vocab_size": 2803 }