|
{ |
|
"architectures": [ |
|
"DebertaV2ForTokenClassification" |
|
], |
|
"attention_probs_dropout_prob": 0.1, |
|
"bos_token_id": 0, |
|
"eos_token_id": 2, |
|
"hidden_act": "gelu", |
|
"hidden_dropout_prob": 0.1, |
|
"hidden_size": 768, |
|
"id2label": { |
|
"0": "ADP", |
|
"1": "ADV", |
|
"2": "AUX", |
|
"3": "AUX+NOUN", |
|
"4": "B-ADP", |
|
"5": "B-ADP+VERB+NOUN", |
|
"6": "B-ADV", |
|
"7": "B-AUX", |
|
"8": "B-AUX+PART", |
|
"9": "B-CCONJ", |
|
"10": "B-DET", |
|
"11": "B-DET+NOUN", |
|
"12": "B-INFR.EV", |
|
"13": "B-INTJ", |
|
"14": "B-NOUN", |
|
"15": "B-NOUN+ADP", |
|
"16": "B-NOUN+ADP+NOUN", |
|
"17": "B-NOUN+ADP+VERB", |
|
"18": "B-NOUN+ADV", |
|
"19": "B-NOUN+NOUN", |
|
"20": "B-NOUN+VERB", |
|
"21": "B-NUM", |
|
"22": "B-NUM+NOUN", |
|
"23": "B-PART", |
|
"24": "B-PART+AUX", |
|
"25": "B-PART+NOUN", |
|
"26": "B-PART+VERB", |
|
"27": "B-PRON", |
|
"28": "B-PROPN", |
|
"29": "B-PUNCT", |
|
"30": "B-SCONJ", |
|
"31": "B-SCONJ+ADV", |
|
"32": "B-VERB", |
|
"33": "B-VERB+NOUN", |
|
"34": "B-VERB+PART", |
|
"35": "B-VERB+SCONJ", |
|
"36": "B-VERT", |
|
"37": "B-X", |
|
"38": "CCONJ", |
|
"39": "DET", |
|
"40": "DET+NOUN", |
|
"41": "DET+SCONJ+VERB", |
|
"42": "I-ADP", |
|
"43": "I-ADP+VERB+NOUN", |
|
"44": "I-ADV", |
|
"45": "I-AUX", |
|
"46": "I-AUX+PART", |
|
"47": "I-CCONJ", |
|
"48": "I-DET", |
|
"49": "I-DET+NOUN", |
|
"50": "I-INFR.EV", |
|
"51": "I-INTJ", |
|
"52": "I-NOUN", |
|
"53": "I-NOUN+ADP", |
|
"54": "I-NOUN+ADP+NOUN", |
|
"55": "I-NOUN+ADP+VERB", |
|
"56": "I-NOUN+ADV", |
|
"57": "I-NOUN+NOUN", |
|
"58": "I-NOUN+VERB", |
|
"59": "I-NUM", |
|
"60": "I-NUM+NOUN", |
|
"61": "I-PART", |
|
"62": "I-PART+AUX", |
|
"63": "I-PART+NOUN", |
|
"64": "I-PART+VERB", |
|
"65": "I-PRON", |
|
"66": "I-PROPN", |
|
"67": "I-PUNCT", |
|
"68": "I-SCONJ", |
|
"69": "I-SCONJ+ADV", |
|
"70": "I-VERB", |
|
"71": "I-VERB+NOUN", |
|
"72": "I-VERB+PART", |
|
"73": "I-VERB+SCONJ", |
|
"74": "I-VERT", |
|
"75": "I-X", |
|
"76": "INTJ", |
|
"77": "NOUN", |
|
"78": "NOUN+ADP", |
|
"79": "NOUN+NOUN", |
|
"80": "NOUN+VERB", |
|
"81": "NUM", |
|
"82": "PART", |
|
"83": "PART+VERB", |
|
"84": "PROPN", |
|
"85": "PUNCT", |
|
"86": "SCONJ", |
|
"87": "SYM", |
|
"88": "VERB", |
|
"89": "VERB+AUX", |
|
"90": "VERB+NOUN", |
|
"91": "VERB+PART", |
|
"92": "VERB+VERB", |
|
"93": "VERT", |
|
"94": "X" |
|
}, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 3072, |
|
"label2id": { |
|
"ADP": 0, |
|
"ADV": 1, |
|
"AUX": 2, |
|
"AUX+NOUN": 3, |
|
"B-ADP": 4, |
|
"B-ADP+VERB+NOUN": 5, |
|
"B-ADV": 6, |
|
"B-AUX": 7, |
|
"B-AUX+PART": 8, |
|
"B-CCONJ": 9, |
|
"B-DET": 10, |
|
"B-DET+NOUN": 11, |
|
"B-INFR.EV": 12, |
|
"B-INTJ": 13, |
|
"B-NOUN": 14, |
|
"B-NOUN+ADP": 15, |
|
"B-NOUN+ADP+NOUN": 16, |
|
"B-NOUN+ADP+VERB": 17, |
|
"B-NOUN+ADV": 18, |
|
"B-NOUN+NOUN": 19, |
|
"B-NOUN+VERB": 20, |
|
"B-NUM": 21, |
|
"B-NUM+NOUN": 22, |
|
"B-PART": 23, |
|
"B-PART+AUX": 24, |
|
"B-PART+NOUN": 25, |
|
"B-PART+VERB": 26, |
|
"B-PRON": 27, |
|
"B-PROPN": 28, |
|
"B-PUNCT": 29, |
|
"B-SCONJ": 30, |
|
"B-SCONJ+ADV": 31, |
|
"B-VERB": 32, |
|
"B-VERB+NOUN": 33, |
|
"B-VERB+PART": 34, |
|
"B-VERB+SCONJ": 35, |
|
"B-VERT": 36, |
|
"B-X": 37, |
|
"CCONJ": 38, |
|
"DET": 39, |
|
"DET+NOUN": 40, |
|
"DET+SCONJ+VERB": 41, |
|
"I-ADP": 42, |
|
"I-ADP+VERB+NOUN": 43, |
|
"I-ADV": 44, |
|
"I-AUX": 45, |
|
"I-AUX+PART": 46, |
|
"I-CCONJ": 47, |
|
"I-DET": 48, |
|
"I-DET+NOUN": 49, |
|
"I-INFR.EV": 50, |
|
"I-INTJ": 51, |
|
"I-NOUN": 52, |
|
"I-NOUN+ADP": 53, |
|
"I-NOUN+ADP+NOUN": 54, |
|
"I-NOUN+ADP+VERB": 55, |
|
"I-NOUN+ADV": 56, |
|
"I-NOUN+NOUN": 57, |
|
"I-NOUN+VERB": 58, |
|
"I-NUM": 59, |
|
"I-NUM+NOUN": 60, |
|
"I-PART": 61, |
|
"I-PART+AUX": 62, |
|
"I-PART+NOUN": 63, |
|
"I-PART+VERB": 64, |
|
"I-PRON": 65, |
|
"I-PROPN": 66, |
|
"I-PUNCT": 67, |
|
"I-SCONJ": 68, |
|
"I-SCONJ+ADV": 69, |
|
"I-VERB": 70, |
|
"I-VERB+NOUN": 71, |
|
"I-VERB+PART": 72, |
|
"I-VERB+SCONJ": 73, |
|
"I-VERT": 74, |
|
"I-X": 75, |
|
"INTJ": 76, |
|
"NOUN": 77, |
|
"NOUN+ADP": 78, |
|
"NOUN+NOUN": 79, |
|
"NOUN+VERB": 80, |
|
"NUM": 81, |
|
"PART": 82, |
|
"PART+VERB": 83, |
|
"PROPN": 84, |
|
"PUNCT": 85, |
|
"SCONJ": 86, |
|
"SYM": 87, |
|
"VERB": 88, |
|
"VERB+AUX": 89, |
|
"VERB+NOUN": 90, |
|
"VERB+PART": 91, |
|
"VERB+VERB": 92, |
|
"VERT": 93, |
|
"X": 94 |
|
}, |
|
"layer_norm_eps": 1e-07, |
|
"max_position_embeddings": 512, |
|
"max_relative_positions": -1, |
|
"model_type": "deberta-v2", |
|
"num_attention_heads": 12, |
|
"num_hidden_layers": 12, |
|
"pad_token_id": 1, |
|
"pooler_dropout": 0, |
|
"pooler_hidden_act": "gelu", |
|
"pooler_hidden_size": 768, |
|
"pos_att_type": [ |
|
"p2c", |
|
"c2p" |
|
], |
|
"position_biased_input": false, |
|
"relative_attention": true, |
|
"task_specific_params": { |
|
"upos_multiword": { |
|
"ADP+VERB+NOUN": { |
|
"tambe": [ |
|
"ta", |
|
"m", |
|
"be" |
|
] |
|
}, |
|
"AUX+NOUN": { |
|
"nep": [ |
|
"ne", |
|
"p" |
|
] |
|
}, |
|
"AUX+PART": { |
|
"nangonna": [ |
|
"nangon", |
|
"na" |
|
], |
|
"nankonna": [ |
|
"nankon", |
|
"na" |
|
] |
|
}, |
|
"DET+NOUN": { |
|
"Tamba": [ |
|
"Tam", |
|
"ba" |
|
], |
|
"Tampa": [ |
|
"Tam", |
|
"pa" |
|
], |
|
"tanpa": [ |
|
"tan", |
|
"pa" |
|
], |
|
"tanto": [ |
|
"tan", |
|
"to" |
|
] |
|
}, |
|
"DET+SCONJ+VERB": { |
|
"Newaan": [ |
|
"Ne", |
|
"wa", |
|
"an" |
|
], |
|
"newaan": [ |
|
"ne", |
|
"wa", |
|
"an" |
|
] |
|
}, |
|
"NOUN+ADP": { |
|
"Kunneiwano": [ |
|
"Kunnei", |
|
"wano" |
|
], |
|
"Orota": [ |
|
"Oro", |
|
"ta" |
|
], |
|
"Orowano": [ |
|
"Oro", |
|
"wano" |
|
], |
|
"Oshmaketa": [ |
|
"Oshmake", |
|
"ta" |
|
], |
|
"Pet-samaketa": [ |
|
"Pet-samake", |
|
"ta" |
|
], |
|
"Soita": [ |
|
"Soi", |
|
"ta" |
|
], |
|
"cheppone": [ |
|
"cheppo", |
|
"ne" |
|
], |
|
"keseta": [ |
|
"kese", |
|
"ta" |
|
], |
|
"kesta": [ |
|
"kes", |
|
"ta" |
|
], |
|
"kunneywano": [ |
|
"kunney", |
|
"wano" |
|
], |
|
"neyta": [ |
|
"ney", |
|
"ta" |
|
], |
|
"orota": [ |
|
"oro", |
|
"ta" |
|
], |
|
"orowa": [ |
|
"oro", |
|
"wa" |
|
], |
|
"orowano": [ |
|
"oro", |
|
"wano" |
|
], |
|
"oshmaketa": [ |
|
"oshmake", |
|
"ta" |
|
], |
|
"otta": [ |
|
"ot", |
|
"ta" |
|
], |
|
"petsamaketa": [ |
|
"petsamake", |
|
"ta" |
|
], |
|
"samaketa": [ |
|
"samake", |
|
"ta" |
|
], |
|
"soyta": [ |
|
"soy", |
|
"ta" |
|
], |
|
"tomta": [ |
|
"tom", |
|
"ta" |
|
] |
|
}, |
|
"NOUN+ADP+NOUN": { |
|
"rorunpurai": [ |
|
"ror", |
|
"un", |
|
"purai" |
|
], |
|
"rorunpuray": [ |
|
"ror", |
|
"un", |
|
"puray" |
|
] |
|
}, |
|
"NOUN+ADP+VERB": { |
|
"soytaarpa": [ |
|
"soy", |
|
"ta", |
|
"arpa" |
|
] |
|
}, |
|
"NOUN+ADV": { |
|
"Tambeta ne": [ |
|
"Tambe", |
|
"ta ne" |
|
] |
|
}, |
|
"NOUN+NOUN": { |
|
"Petetoko": [ |
|
"Pet", |
|
"etoko" |
|
], |
|
"Shirokanipe": [ |
|
"Shirokani", |
|
"pe" |
|
], |
|
"Tambet aaye": [ |
|
"Tambe", |
|
"t aaye" |
|
], |
|
"hekattar": [ |
|
"hekat", |
|
"tar" |
|
], |
|
"inaanpe": [ |
|
"inaan", |
|
"pe" |
|
], |
|
"inanpe": [ |
|
"inan", |
|
"pe" |
|
], |
|
"iporohoka": [ |
|
"iporoho", |
|
"ka" |
|
], |
|
"kamuinish": [ |
|
"kamui", |
|
"nish" |
|
], |
|
"kamuynis": [ |
|
"kamuy", |
|
"nis" |
|
], |
|
"konkanipe": [ |
|
"konkani", |
|
"pe" |
|
], |
|
"petetok": [ |
|
"pet", |
|
"etok" |
|
], |
|
"petetoko": [ |
|
"pet", |
|
"etoko" |
|
], |
|
"sirokanipe": [ |
|
"sirokani", |
|
"pe" |
|
] |
|
}, |
|
"NOUN+VERB": { |
|
"Omakun": [ |
|
"Omak", |
|
"un" |
|
], |
|
"Orepun": [ |
|
"Orep", |
|
"un" |
|
], |
|
"Shiriki": [ |
|
"Shiri", |
|
"ki" |
|
], |
|
"kotankor": [ |
|
"kotan", |
|
"kor" |
|
], |
|
"makun": [ |
|
"mak", |
|
"un" |
|
], |
|
"repun": [ |
|
"rep", |
|
"un" |
|
], |
|
"rikunruke": [ |
|
"rik", |
|
"unruke" |
|
], |
|
"siriki": [ |
|
"siri", |
|
"ki" |
|
], |
|
"ukakushte": [ |
|
"uka", |
|
"kushte" |
|
], |
|
"ukakuste": [ |
|
"uka", |
|
"kuste" |
|
], |
|
"uraikik": [ |
|
"urai", |
|
"kik" |
|
] |
|
}, |
|
"NUM+NOUN": { |
|
"Wanto": [ |
|
"Wan", |
|
"to" |
|
], |
|
"hotnepa": [ |
|
"hotne", |
|
"pa" |
|
], |
|
"wanpe": [ |
|
"wan", |
|
"pe" |
|
], |
|
"wanto": [ |
|
"wan", |
|
"to" |
|
] |
|
}, |
|
"PART+AUX": { |
|
"chine": [ |
|
"chi", |
|
"ne" |
|
] |
|
}, |
|
"PART+NOUN": { |
|
"=anpe": [ |
|
"=an", |
|
"pe" |
|
], |
|
"eisam": [ |
|
"ei", |
|
"sam" |
|
] |
|
}, |
|
"PART+VERB": { |
|
"ainu-wap": [ |
|
"a", |
|
"inu-wap" |
|
], |
|
"akus": [ |
|
"a", |
|
"kus" |
|
], |
|
"chiki": [ |
|
"chi", |
|
"ki" |
|
], |
|
"chikik": [ |
|
"chi", |
|
"kik" |
|
], |
|
"eram an": [ |
|
"e", |
|
"ram an" |
|
], |
|
"eramasu": [ |
|
"e", |
|
"ramasu" |
|
], |
|
"karapa": [ |
|
"k", |
|
"arapa" |
|
] |
|
}, |
|
"SCONJ+ADV": { |
|
"koiramno": [ |
|
"ko", |
|
"iramno" |
|
] |
|
}, |
|
"VERB+AUX": { |
|
"sattek": [ |
|
"sat", |
|
"tek" |
|
] |
|
}, |
|
"VERB+NOUN": { |
|
"Hesepa": [ |
|
"Hese", |
|
"pa" |
|
], |
|
"ambe": [ |
|
"am", |
|
"be" |
|
], |
|
"anpe": [ |
|
"an", |
|
"pe" |
|
], |
|
"anto": [ |
|
"an", |
|
"to" |
|
], |
|
"h\u00e9sep\u00e1ha": [ |
|
"h\u00e9se", |
|
"p\u00e1ha" |
|
], |
|
"kari": [ |
|
"kar", |
|
"i" |
|
], |
|
"wenpuri": [ |
|
"wen", |
|
"puri" |
|
] |
|
}, |
|
"VERB+PART": { |
|
"kari": [ |
|
"kar", |
|
"i" |
|
], |
|
"rokash": [ |
|
"rok", |
|
"ash" |
|
], |
|
"sapash": [ |
|
"sap", |
|
"ash" |
|
], |
|
"shinotash": [ |
|
"shinot", |
|
"ash" |
|
] |
|
}, |
|
"VERB+SCONJ": { |
|
"anak un": [ |
|
"an", |
|
"ak un" |
|
], |
|
"anakanakne": [ |
|
"an", |
|
"akanakne" |
|
], |
|
"sakno": [ |
|
"sak", |
|
"no" |
|
] |
|
}, |
|
"VERB+VERB": { |
|
"ranran": [ |
|
"ran", |
|
"ran" |
|
] |
|
} |
|
} |
|
}, |
|
"tokenizer_class": "DebertaV2TokenizerFast", |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.25.1", |
|
"type_vocab_size": 0, |
|
"vocab_size": 6143 |
|
} |
|
|