re-initialize

suparkanbun/models/guwenbert-base.pos/config.json

@@ -0,0 +1,291 @@
+{
+  "_name_or_path": "ethanyt/guwenbert-base",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "n,代名詞,人称,他,PRON,Person=1|PronType=Prs",
+    "1": "n,代名詞,人称,他,PRON,Person=2|PronType=Prs",
+    "2": "n,代名詞,人称,他,PRON,Person=3|PronType=Prs",
+    "3": "n,代名詞,人称,他,PRON,PronType=Prs",
+    "4": "n,代名詞,人称,他,PRON,PronType=Prs|Reflex=Yes",
+    "5": "n,代名詞,人称,止格,PRON,Person=1|PronType=Prs",
+    "6": "n,代名詞,人称,止格,PRON,Person=2|PronType=Prs",
+    "7": "n,代名詞,人称,止格,PRON,Person=3|PronType=Prs",
+    "8": "n,代名詞,人称,止格,PRON,PronType=Prs",
+    "9": "n,代名詞,人称,起格,PRON,Person=1|PronType=Prs",
+    "10": "n,代名詞,人称,起格,PRON,Person=2|PronType=Prs",
+    "11": "n,代名詞,人称,起格,PRON,Person=3|PronType=Prs",
+    "12": "n,代名詞,人称,起格,PRON,PronType=Prs",
+    "13": "n,代名詞,指示,*,PRON,PronType=Dem",
+    "14": "n,代名詞,疑問,*,PRON,PronType=Int",
+    "15": "n,名詞,不可譲,属性,NOUN,_",
+    "16": "n,名詞,不可譲,疾病,NOUN,_",
+    "17": "n,名詞,不可譲,身体,NOUN,_",
+    "18": "n,名詞,主体,動物,NOUN,_",
+    "19": "n,名詞,主体,国名,PROPN,Case=Loc|NameType=Nat",
+    "20": "n,名詞,主体,書物,NOUN,_",
+    "21": "n,名詞,主体,機関,NOUN,_",
+    "22": "n,名詞,主体,集団,NOUN,_",
+    "23": "n,名詞,人,その他の人名,PROPN,NameType=Prs",
+    "24": "n,名詞,人,人,NOUN,_",
+    "25": "n,名詞,人,名,PROPN,NameType=Giv",
+    "26": "n,名詞,人,姓氏,PROPN,NameType=Sur",
+    "27": "n,名詞,人,役割,NOUN,_",
+    "28": "n,名詞,人,複合的人名,PROPN,NameType=Prs",
+    "29": "n,名詞,人,関係,NOUN,_",
+    "30": "n,名詞,制度,儀礼,NOUN,_",
+    "31": "n,名詞,制度,場,NOUN,Case=Loc",
+    "32": "n,名詞,可搬,乗り物,NOUN,_",
+    "33": "n,名詞,可搬,伝達,NOUN,_",
+    "34": "n,名詞,可搬,成果物,NOUN,_",
+    "35": "n,名詞,可搬,糧食,NOUN,_",
+    "36": "n,名詞,可搬,道具,NOUN,_",
+    "37": "n,名詞,固定物,地名,PROPN,Case=Loc|NameType=Geo",
+    "38": "n,名詞,固定物,地形,NOUN,Case=Loc",
+    "39": "n,名詞,固定物,建造物,NOUN,Case=Loc",
+    "40": "n,名詞,固定物,樹木,NOUN,_",
+    "41": "n,名詞,固定物,関係,NOUN,Case=Loc",
+    "42": "n,名詞,外観,人,NOUN,_",
+    "43": "n,名詞,天象,天文,NOUN,_",
+    "44": "n,名詞,天象,怪異,NOUN,_",
+    "45": "n,名詞,天象,気象,NOUN,_",
+    "46": "n,名詞,度量衡,*,NOUN,NounType=Clf",
+    "47": "n,名詞,思考,*,NOUN,_",
+    "48": "n,名詞,描写,形質,NOUN,_",
+    "49": "n,名詞,描写,態度,NOUN,_",
+    "50": "n,名詞,数量,*,NOUN,_",
+    "51": "n,名詞,時,*,NOUN,Case=Tem",
+    "52": "n,名詞,行為,*,NOUN,_",
+    "53": "n,数詞,干支,*,NUM,NumType=Ord",
+    "54": "n,数詞,数,*,NUM,_",
+    "55": "n,数詞,数字,*,NUM,_",
+    "56": "p,助詞,句末,*,PART,_",
+    "57": "p,助詞,句頭,*,PART,_",
+    "58": "p,助詞,接続,並列,CCONJ,_",
+    "59": "p,助詞,接続,体言化,PART,_",
+    "60": "p,助詞,接続,属格,SCONJ,_",
+    "61": "p,助詞,提示,*,PART,_",
+    "62": "p,感嘆詞,*,*,INTJ,_",
+    "63": "p,接尾辞,*,*,PART,_",
+    "64": "s,文字,*,*,SYM,_",
+    "65": "s,記号,一般,*,SYM,_",
+    "66": "s,記号,句点,*,PUNCT,_",
+    "67": "s,記号,読点,*,PUNCT,_",
+    "68": "v,前置詞,基盤,*,ADP,_",
+    "69": "v,前置詞,源泉,*,ADP,_",
+    "70": "v,前置詞,経由,*,ADP,_",
+    "71": "v,前置詞,関係,*,ADP,_",
+    "72": "v,副詞,判断,推定,ADV,_",
+    "73": "v,副詞,判断,確定,ADV,_",
+    "74": "v,副詞,判断,逆接,ADV,_",
+    "75": "v,副詞,否定,体言否定,ADV,Polarity=Neg",
+    "76": "v,副詞,否定,有界,ADV,Polarity=Neg",
+    "77": "v,副詞,否定,無界,ADV,Polarity=Neg",
+    "78": "v,副詞,否定,禁止,ADV,Polarity=Neg",
+    "79": "v,副詞,描写,*,ADV,_",
+    "80": "v,副詞,時相,変化,ADV,AdvType=Tim",
+    "81": "v,副詞,時相,完了,ADV,AdvType=Tim|Aspect=Perf",
+    "82": "v,副詞,時相,将来,ADV,AdvType=Tim|Tense=Fut",
+    "83": "v,副詞,時相,恒常,ADV,AdvType=Tim",
+    "84": "v,副詞,時相,現在,ADV,AdvType=Tim|Tense=Pres",
+    "85": "v,副詞,時相,終局,ADV,AdvType=Tim",
+    "86": "v,副詞,時相,継起,ADV,AdvType=Tim",
+    "87": "v,副詞,時相,緊接,ADV,AdvType=Tim",
+    "88": "v,副詞,時相,過去,ADV,AdvType=Tim|Tense=Past",
+    "89": "v,副詞,疑問,原因,ADV,AdvType=Cau",
+    "90": "v,副詞,疑問,反語,ADV,_",
+    "91": "v,副詞,疑問,所在,ADV,_",
+    "92": "v,副詞,程度,やや高度,ADV,AdvType=Deg|Degree=Cmp",
+    "93": "v,副詞,程度,極度,ADV,AdvType=Deg|Degree=Sup",
+    "94": "v,副詞,程度,軽度,ADV,AdvType=Deg|Degree=Pos",
+    "95": "v,副詞,範囲,共同,ADV,_",
+    "96": "v,副詞,範囲,総括,ADV,_",
+    "97": "v,副詞,範囲,限定,ADV,_",
+    "98": "v,副詞,頻度,偶発,ADV,_",
+    "99": "v,副詞,頻度,重複,ADV,_",
+    "100": "v,副詞,頻度,頻繁,ADV,_",
+    "101": "v,助動詞,受動,*,AUX,Voice=Pass",
+    "102": "v,助動詞,可能,*,AUX,Mood=Pot",
+    "103": "v,助動詞,必要,*,AUX,Mood=Nec",
+    "104": "v,助動詞,願望,*,AUX,Mood=Des",
+    "105": "v,動詞,変化,制度,VERB,_",
+    "106": "v,動詞,変化,性質,VERB,_",
+    "107": "v,動詞,変化,生物,VERB,_",
+    "108": "v,動詞,存在,存在,VERB,Polarity=Neg",
+    "109": "v,動詞,存在,存在,VERB,VerbType=Cop",
+    "110": "v,動詞,存在,存在,VERB,_",
+    "111": "v,動詞,描写,境遇,VERB,Degree=Pos",
+    "112": "v,動詞,描写,形質,VERB,Degree=Pos",
+    "113": "v,動詞,描写,態度,VERB,Degree=Pos",
+    "114": "v,動詞,描写,量,VERB,Degree=Pos",
+    "115": "v,動詞,行為,交流,VERB,_",
+    "116": "v,動詞,行為,伝達,VERB,_",
+    "117": "v,動詞,行為,使役,VERB,_",
+    "118": "v,動詞,行為,儀礼,VERB,_",
+    "119": "v,動詞,行為,分類,VERB,Degree=Equ",
+    "120": "v,動詞,行為,動作,VERB,_",
+    "121": "v,動詞,行為,姿勢,VERB,_",
+    "122": "v,動詞,行為,役割,VERB,_",
+    "123": "v,動詞,行為,得失,VERB,_",
+    "124": "v,動詞,行為,態度,VERB,_",
+    "125": "v,動詞,行為,生産,VERB,_",
+    "126": "v,動詞,行為,移動,VERB,_",
+    "127": "v,動詞,行為,設置,VERB,_",
+    "128": "v,動詞,行為,飲食,VERB,_"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "n,代名詞,人称,他,PRON,Person=1|PronType=Prs": 0,
+    "n,代名詞,人称,他,PRON,Person=2|PronType=Prs": 1,
+    "n,代名詞,人称,他,PRON,Person=3|PronType=Prs": 2,
+    "n,代名詞,人称,他,PRON,PronType=Prs": 3,
+    "n,代名詞,人称,他,PRON,PronType=Prs|Reflex=Yes": 4,
+    "n,代名詞,人称,止格,PRON,Person=1|PronType=Prs": 5,
+    "n,代名詞,人称,止格,PRON,Person=2|PronType=Prs": 6,
+    "n,代名詞,人称,止格,PRON,Person=3|PronType=Prs": 7,
+    "n,代名詞,人称,止格,PRON,PronType=Prs": 8,
+    "n,代名詞,人称,起格,PRON,Person=1|PronType=Prs": 9,
+    "n,代名詞,人称,起格,PRON,Person=2|PronType=Prs": 10,
+    "n,代名詞,人称,起格,PRON,Person=3|PronType=Prs": 11,
+    "n,代名詞,人称,起格,PRON,PronType=Prs": 12,
+    "n,代名詞,指示,*,PRON,PronType=Dem": 13,
+    "n,代名詞,疑問,*,PRON,PronType=Int": 14,
+    "n,名詞,不可譲,属性,NOUN,_": 15,
+    "n,名詞,不可譲,疾病,NOUN,_": 16,
+    "n,名詞,不可譲,身体,NOUN,_": 17,
+    "n,名詞,主体,動物,NOUN,_": 18,
+    "n,名詞,主体,国名,PROPN,Case=Loc|NameType=Nat": 19,
+    "n,名詞,主体,書物,NOUN,_": 20,
+    "n,名詞,主体,機関,NOUN,_": 21,
+    "n,名詞,主体,集団,NOUN,_": 22,
+    "n,名詞,人,その他の人名,PROPN,NameType=Prs": 23,
+    "n,名詞,人,人,NOUN,_": 24,
+    "n,名詞,人,名,PROPN,NameType=Giv": 25,
+    "n,名詞,人,姓氏,PROPN,NameType=Sur": 26,
+    "n,名詞,人,役割,NOUN,_": 27,
+    "n,名詞,人,複合的人名,PROPN,NameType=Prs": 28,
+    "n,名詞,人,関係,NOUN,_": 29,
+    "n,名詞,制度,儀礼,NOUN,_": 30,
+    "n,名詞,制度,場,NOUN,Case=Loc": 31,
+    "n,名詞,可搬,乗り物,NOUN,_": 32,
+    "n,名詞,可搬,伝達,NOUN,_": 33,
+    "n,名詞,可搬,成果物,NOUN,_": 34,
+    "n,名詞,可搬,糧食,NOUN,_": 35,
+    "n,名詞,可搬,道具,NOUN,_": 36,
+    "n,名詞,固定物,地名,PROPN,Case=Loc|NameType=Geo": 37,
+    "n,名詞,固定物,地形,NOUN,Case=Loc": 38,
+    "n,名詞,固定物,建造物,NOUN,Case=Loc": 39,
+    "n,名詞,固定物,樹木,NOUN,_": 40,
+    "n,名詞,固定物,関係,NOUN,Case=Loc": 41,
+    "n,名詞,外観,人,NOUN,_": 42,
+    "n,名詞,天象,天文,NOUN,_": 43,
+    "n,名詞,天象,怪異,NOUN,_": 44,
+    "n,名詞,天象,気象,NOUN,_": 45,
+    "n,名詞,度量衡,*,NOUN,NounType=Clf": 46,
+    "n,名詞,思考,*,NOUN,_": 47,
+    "n,名詞,描写,形質,NOUN,_": 48,
+    "n,名詞,描写,態度,NOUN,_": 49,
+    "n,名詞,数量,*,NOUN,_": 50,
+    "n,名詞,時,*,NOUN,Case=Tem": 51,
+    "n,名詞,行為,*,NOUN,_": 52,
+    "n,数詞,干支,*,NUM,NumType=Ord": 53,
+    "n,数詞,数,*,NUM,_": 54,
+    "n,数詞,数字,*,NUM,_": 55,
+    "p,助詞,句末,*,PART,_": 56,
+    "p,助詞,句頭,*,PART,_": 57,
+    "p,助詞,接続,並列,CCONJ,_": 58,
+    "p,助詞,接続,体言化,PART,_": 59,
+    "p,助詞,接続,属格,SCONJ,_": 60,
+    "p,助詞,提示,*,PART,_": 61,
+    "p,感嘆詞,*,*,INTJ,_": 62,
+    "p,接尾辞,*,*,PART,_": 63,
+    "s,文字,*,*,SYM,_": 64,
+    "s,記号,一般,*,SYM,_": 65,
+    "s,記号,句点,*,PUNCT,_": 66,
+    "s,記号,読点,*,PUNCT,_": 67,
+    "v,前置詞,基盤,*,ADP,_": 68,
+    "v,前置詞,源泉,*,ADP,_": 69,
+    "v,前置詞,経由,*,ADP,_": 70,
+    "v,前置詞,関係,*,ADP,_": 71,
+    "v,副詞,判断,推定,ADV,_": 72,
+    "v,副詞,判断,確定,ADV,_": 73,
+    "v,副詞,判断,逆接,ADV,_": 74,
+    "v,副詞,否定,体言否定,ADV,Polarity=Neg": 75,
+    "v,副詞,否定,有界,ADV,Polarity=Neg": 76,
+    "v,副詞,否定,無界,ADV,Polarity=Neg": 77,
+    "v,副詞,否定,禁止,ADV,Polarity=Neg": 78,
+    "v,副詞,描写,*,ADV,_": 79,
+    "v,副詞,時相,変化,ADV,AdvType=Tim": 80,
+    "v,副詞,時相,完了,ADV,AdvType=Tim|Aspect=Perf": 81,
+    "v,副詞,時相,将来,ADV,AdvType=Tim|Tense=Fut": 82,
+    "v,副詞,時相,恒常,ADV,AdvType=Tim": 83,
+    "v,副詞,時相,現在,ADV,AdvType=Tim|Tense=Pres": 84,
+    "v,副詞,時相,終局,ADV,AdvType=Tim": 85,
+    "v,副詞,時相,継起,ADV,AdvType=Tim": 86,
+    "v,副詞,時相,緊接,ADV,AdvType=Tim": 87,
+    "v,副詞,時相,過去,ADV,AdvType=Tim|Tense=Past": 88,
+    "v,副詞,疑問,原因,ADV,AdvType=Cau": 89,
+    "v,副詞,疑問,反語,ADV,_": 90,
+    "v,副詞,疑問,所在,ADV,_": 91,
+    "v,副詞,程度,やや高度,ADV,AdvType=Deg|Degree=Cmp": 92,
+    "v,副詞,程度,極度,ADV,AdvType=Deg|Degree=Sup": 93,
+    "v,副詞,程度,軽度,ADV,AdvType=Deg|Degree=Pos": 94,
+    "v,副詞,範囲,共同,ADV,_": 95,
+    "v,副詞,範囲,総括,ADV,_": 96,
+    "v,副詞,範囲,限定,ADV,_": 97,
+    "v,副詞,頻度,偶発,ADV,_": 98,
+    "v,副詞,頻度,重複,ADV,_": 99,
+    "v,副詞,頻度,頻繁,ADV,_": 100,
+    "v,助動詞,受動,*,AUX,Voice=Pass": 101,
+    "v,助動詞,可能,*,AUX,Mood=Pot": 102,
+    "v,助動詞,必要,*,AUX,Mood=Nec": 103,
+    "v,助動詞,願望,*,AUX,Mood=Des": 104,
+    "v,動詞,変化,制度,VERB,_": 105,
+    "v,動詞,変化,性質,VERB,_": 106,
+    "v,動詞,変化,生物,VERB,_": 107,
+    "v,動詞,存在,存在,VERB,Polarity=Neg": 108,
+    "v,動詞,存在,存在,VERB,VerbType=Cop": 109,
+    "v,動詞,存在,存在,VERB,_": 110,
+    "v,動詞,描写,境遇,VERB,Degree=Pos": 111,
+    "v,動詞,描写,形質,VERB,Degree=Pos": 112,
+    "v,動詞,描写,態度,VERB,Degree=Pos": 113,
+    "v,動詞,描写,量,VERB,Degree=Pos": 114,
+    "v,動詞,行為,交流,VERB,_": 115,
+    "v,動詞,行為,伝達,VERB,_": 116,
+    "v,動詞,行為,使役,VERB,_": 117,
+    "v,動詞,行為,儀礼,VERB,_": 118,
+    "v,動詞,行為,分類,VERB,Degree=Equ": 119,
+    "v,動詞,行為,動作,VERB,_": 120,
+    "v,動詞,行為,姿勢,VERB,_": 121,
+    "v,動詞,行為,役割,VERB,_": 122,
+    "v,動詞,行為,得失,VERB,_": 123,
+    "v,動詞,行為,態度,VERB,_": 124,
+    "v,動詞,行為,生産,VERB,_": 125,
+    "v,動詞,行為,移動,VERB,_": 126,
+    "v,動詞,行為,設置,VERB,_": 127,
+    "v,動詞,行為,飲食,VERB,_": 128
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 23292
+}

suparkanbun/models/guwenbert-base.pos/filesize.txt

@@ -0,0 +1,2 @@
+pytorch_model.bin 413843728
+guwenbert-base.supar 463070836

suparkanbun/models/guwenbert-base.pos/guwenbert-base.supar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0dff1df3a532e5570a80fe56cb1345bfa2c6018df1a80f351906e1ad7b2b416
+size 463070836

suparkanbun/models/guwenbert-base.pos/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12f3d827a041fe44879e25031ba74bec5c6f7408b211dff0b2ebedbf8c40dace
+size 413843728

suparkanbun/models/guwenbert-base.pos/special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

suparkanbun/models/guwenbert-base.pos/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "ethanyt/guwenbert-base", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}