{ "architectures": [ "ModernBertForTokenClassification" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 2, "classifier_activation": "gelu", "classifier_bias": false, "classifier_dropout": 0.0, "classifier_pooling": "mean", "cls_token_id": 1, "decoder_bias": true, "deterministic_flash_attn": false, "dtype": "float32", "embedding_dropout": 0.0, "eos_token_id": 1, "global_attn_every_n_layers": 3, "global_rope_theta": 160000, "gradient_checkpointing": false, "hidden_activation": "gelu", "hidden_size": 384, "id2label": { "0": "afr_Latn", "1": "als_Latn", "2": "amh_Ethi", "3": "ara_Arab", "4": "asm_Beng", "5": "azj_Latn", "6": "bam_Latn", "7": "ben_Beng", "8": "bod_Tibt", "9": "bul_Cyrl", "10": "cat_Latn", "11": "ceb_Latn", "12": "ces_Latn", "13": "ckb_Arab", "14": "cmn_Hans", "15": "cmn_Hant", "16": "dan_Latn", "17": "deu_Latn", "18": "ekk_Latn", "19": "ell_Grek", "20": "eng_Latn", "21": "eus_Latn", "22": "fas_Arab", "23": "fil_Latn", "24": "fin_Latn", "25": "fra_Latn", "26": "fuv_Latn", "27": "gaz_Latn", "28": "gug_Latn", "29": "guj_Gujr", "30": "hat_Latn", "31": "hau_Latn", "32": "heb_Hebr", "33": "hin_Deva", "34": "hrv_Latn", "35": "hun_Latn", "36": "hye_Armn", "37": "ibo_Latn", "38": "ilo_Latn", "39": "ind_Latn", "40": "isl_Latn", "41": "ita_Latn", "42": "jav_Latn", "43": "jpn_Jpan", "44": "kac_Latn", "45": "kan_Knda", "46": "kat_Geor", "47": "kaz_Cyrl", "48": "kea_Latn", "49": "khk_Cyrl", "50": "khm_Khmr", "51": "kin_Latn", "52": "kir_Cyrl", "53": "kor_Hang", "54": "lao_Laoo", "55": "lin_Latn", "56": "lit_Latn", "57": "lug_Latn", "58": "luo_Latn", "59": "lvs_Latn", "60": "mal_Mlym", "61": "mar_Deva", "62": "mkd_Cyrl", "63": "mlt_Latn", "64": "mri_Latn", "65": "mya_Mymr", "66": "nld_Latn", "67": "nob_Latn", "68": "npi_Deva", "69": "nso_Latn", "70": "nya_Latn", "71": "ory_Orya", "72": "pan_Guru", "73": "pbt_Arab", "74": "plt_Latn", "75": "pol_Latn", "76": "por_Latn", "77": "ron_Latn", "78": "rus_Cyrl", "79": "shn_Mymr", "80": "sin_Sinh", "81": "slk_Latn", "82": "slv_Latn", "83": "sna_Latn", "84": "snd_Arab", "85": "som_Latn", "86": "sot_Latn", "87": "spa_Latn", "88": "srp_Cyrl", "89": "ssw_Latn", "90": "sun_Latn", "91": "swe_Latn", "92": "swh_Latn", "93": "tam_Taml", "94": "tel_Telu", "95": "tgk_Cyrl", "96": "tha_Thai", "97": "tir_Ethi", "98": "tsn_Latn", "99": "tso_Latn", "100": "tur_Latn", "101": "ukr_Cyrl", "102": "urd_Arab", "103": "uzn_Latn", "104": "vie_Latn", "105": "war_Latn", "106": "wol_Latn", "107": "xho_Latn", "108": "yor_Latn", "109": "zsm_Latn", "110": "zul_Latn", "111": "NUM", "112": "PUNCT", "113": "SYM" }, "initializer_cutoff_factor": 2.0, "initializer_range": 0.02, "intermediate_size": 1152, "label2id": { "NUM": 111, "PUNCT": 112, "SYM": 113, "afr_Latn": 0, "als_Latn": 1, "amh_Ethi": 2, "ara_Arab": 3, "asm_Beng": 4, "azj_Latn": 5, "bam_Latn": 6, "ben_Beng": 7, "bod_Tibt": 8, "bul_Cyrl": 9, "cat_Latn": 10, "ceb_Latn": 11, "ces_Latn": 12, "ckb_Arab": 13, "cmn_Hans": 14, "cmn_Hant": 15, "dan_Latn": 16, "deu_Latn": 17, "ekk_Latn": 18, "ell_Grek": 19, "eng_Latn": 20, "eus_Latn": 21, "fas_Arab": 22, "fil_Latn": 23, "fin_Latn": 24, "fra_Latn": 25, "fuv_Latn": 26, "gaz_Latn": 27, "gug_Latn": 28, "guj_Gujr": 29, "hat_Latn": 30, "hau_Latn": 31, "heb_Hebr": 32, "hin_Deva": 33, "hrv_Latn": 34, "hun_Latn": 35, "hye_Armn": 36, "ibo_Latn": 37, "ilo_Latn": 38, "ind_Latn": 39, "isl_Latn": 40, "ita_Latn": 41, "jav_Latn": 42, "jpn_Jpan": 43, "kac_Latn": 44, "kan_Knda": 45, "kat_Geor": 46, "kaz_Cyrl": 47, "kea_Latn": 48, "khk_Cyrl": 49, "khm_Khmr": 50, "kin_Latn": 51, "kir_Cyrl": 52, "kor_Hang": 53, "lao_Laoo": 54, "lin_Latn": 55, "lit_Latn": 56, "lug_Latn": 57, "luo_Latn": 58, "lvs_Latn": 59, "mal_Mlym": 60, "mar_Deva": 61, "mkd_Cyrl": 62, "mlt_Latn": 63, "mri_Latn": 64, "mya_Mymr": 65, "nld_Latn": 66, "nob_Latn": 67, "npi_Deva": 68, "nso_Latn": 69, "nya_Latn": 70, "ory_Orya": 71, "pan_Guru": 72, "pbt_Arab": 73, "plt_Latn": 74, "pol_Latn": 75, "por_Latn": 76, "ron_Latn": 77, "rus_Cyrl": 78, "shn_Mymr": 79, "sin_Sinh": 80, "slk_Latn": 81, "slv_Latn": 82, "sna_Latn": 83, "snd_Arab": 84, "som_Latn": 85, "sot_Latn": 86, "spa_Latn": 87, "srp_Cyrl": 88, "ssw_Latn": 89, "sun_Latn": 90, "swe_Latn": 91, "swh_Latn": 92, "tam_Taml": 93, "tel_Telu": 94, "tgk_Cyrl": 95, "tha_Thai": 96, "tir_Ethi": 97, "tsn_Latn": 98, "tso_Latn": 99, "tur_Latn": 100, "ukr_Cyrl": 101, "urd_Arab": 102, "uzn_Latn": 103, "vie_Latn": 104, "war_Latn": 105, "wol_Latn": 106, "xho_Latn": 107, "yor_Latn": 108, "zsm_Latn": 109, "zul_Latn": 110 }, "layer_norm_eps": 1e-05, "local_attention": 128, "local_rope_theta": 160000, "mask_token_id": 4, "max_position_embeddings": 8192, "mlp_bias": false, "mlp_dropout": 0.0, "model_type": "modernbert", "norm_bias": false, "norm_eps": 1e-05, "num_attention_heads": 6, "num_hidden_layers": 22, "pad_token_id": 0, "position_embedding_type": "sans_pos", "repad_logits_with_grad": false, "sep_token_id": 1, "sparse_pred_ignore_index": -100, "sparse_prediction": false, "transformers_version": "4.57.0", "vocab_size": 256000, "auto_map": { "AutoModel": "modeling_mixlid.MixLIDForTokenClassification", "AutoModelForTokenClassification": "modeling_mixlid.MixLIDForTokenClassification" } }