upload model files
Browse files- README.md +25 -0
- config.json +232 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
README.md
CHANGED
@@ -1,3 +1,28 @@
|
|
1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
license: gpl-3.0
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- zh
|
4 |
+
thumbnail: https://ckip.iis.sinica.edu.tw/files/ckip_logo.png
|
5 |
+
tags:
|
6 |
+
- pytorch
|
7 |
+
- token-classification
|
8 |
+
- bert
|
9 |
+
- zh
|
10 |
license: gpl-3.0
|
11 |
---
|
12 |
+
|
13 |
+
# CKIP BERT Base Han Chinese POS
|
14 |
+
|
15 |
+
This model provides part-of-speech (POS) tagging for the ancient Chinese language. Our training dataset covers four eras of the Chinese language.
|
16 |
+
|
17 |
+
## Homepage
|
18 |
+
* [ckiplab/han-transformers](https://github.com/ckiplab/han-transformers)
|
19 |
+
|
20 |
+
## Training Datasets
|
21 |
+
The copyright of the datasets belongs to the Institute of Linguistics, Academia Sinica.
|
22 |
+
* [中央研究院上古漢語標記語料庫](http://lingcorpus.iis.sinica.edu.tw/cgi-bin/kiwi/akiwi/kiwi.sh)
|
23 |
+
* [中央研究院中古漢語語料庫](http://lingcorpus.iis.sinica.edu.tw/cgi-bin/kiwi/dkiwi/kiwi.sh)
|
24 |
+
* [中央研究院近代漢語語料庫](http://lingcorpus.iis.sinica.edu.tw/cgi-bin/kiwi/pkiwi/kiwi.sh)
|
25 |
+
* [中央研究院現代漢語語料庫](http://asbc.iis.sinica.edu.tw)
|
26 |
+
|
27 |
+
## Contributors
|
28 |
+
* Chin-Tung Lin at [CKIP](https://ckip.iis.sinica.edu.tw/)
|
config.json
ADDED
@@ -0,0 +1,232 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "hub/ckiplab/bert-base-chinese-20210817-001848",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"directionality": "bidi",
|
8 |
+
"finetuning_task": "ner",
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"label2id": {
|
14 |
+
"571": 53,
|
15 |
+
"A": 41,
|
16 |
+
"C": 86,
|
17 |
+
"COLONCATEGORY": 49,
|
18 |
+
"COMMACATEGORY": 32,
|
19 |
+
"Caa": 34,
|
20 |
+
"Cbb": 20,
|
21 |
+
"D": 74,
|
22 |
+
"DASHCATEGORY": 56,
|
23 |
+
"DAb": 92,
|
24 |
+
"DC": 97,
|
25 |
+
"DE": 29,
|
26 |
+
"DFa": 80,
|
27 |
+
"DH": 88,
|
28 |
+
"DJ": 91,
|
29 |
+
"Da": 89,
|
30 |
+
"Daa": 40,
|
31 |
+
"Dab": 28,
|
32 |
+
"Db": 95,
|
33 |
+
"Dba": 45,
|
34 |
+
"Dbb": 43,
|
35 |
+
"Dc": 12,
|
36 |
+
"Dd": 19,
|
37 |
+
"Df": 94,
|
38 |
+
"Dfa": 37,
|
39 |
+
"Dfb": 59,
|
40 |
+
"Dg": 61,
|
41 |
+
"Dh": 27,
|
42 |
+
"Di": 81,
|
43 |
+
"Dj": 39,
|
44 |
+
"Dk": 52,
|
45 |
+
"Dl": 18,
|
46 |
+
"EXCLAMATIONCATEGORY": 50,
|
47 |
+
"EXCLANATIONCATEGORY": 79,
|
48 |
+
"FW": 64,
|
49 |
+
"I": 57,
|
50 |
+
"N": 78,
|
51 |
+
"NA": 93,
|
52 |
+
"NB": 77,
|
53 |
+
"ND": 76,
|
54 |
+
"NH": 70,
|
55 |
+
"Na": 0,
|
56 |
+
"Nb": 9,
|
57 |
+
"Nc": 7,
|
58 |
+
"Nd": 11,
|
59 |
+
"Ne": 85,
|
60 |
+
"Neqa": 31,
|
61 |
+
"Nes": 25,
|
62 |
+
"Neu": 8,
|
63 |
+
"Nf": 33,
|
64 |
+
"Ng": 22,
|
65 |
+
"Nh": 4,
|
66 |
+
"P": 10,
|
67 |
+
"PARENTHES7ISCATEGORY": 90,
|
68 |
+
"PARENTHESISCATEGORY": 51,
|
69 |
+
"PAUSECATEGORY": 58,
|
70 |
+
"PERIODCATEGORY": 1,
|
71 |
+
"Q": 62,
|
72 |
+
"QUESTIONCATEGORY": 48,
|
73 |
+
"R": 47,
|
74 |
+
"SEMICOLONCATEGORY": 55,
|
75 |
+
"SHI": 38,
|
76 |
+
"T": 26,
|
77 |
+
"T3": 82,
|
78 |
+
"T4": 66,
|
79 |
+
"T5": 46,
|
80 |
+
"T6": 42,
|
81 |
+
"T7": 54,
|
82 |
+
"T8": 15,
|
83 |
+
"U": 60,
|
84 |
+
"V": 72,
|
85 |
+
"VA": 23,
|
86 |
+
"VAC": 30,
|
87 |
+
"VB": 63,
|
88 |
+
"VC": 3,
|
89 |
+
"VCL": 13,
|
90 |
+
"VD": 35,
|
91 |
+
"VE": 5,
|
92 |
+
"VF": 36,
|
93 |
+
"VG": 21,
|
94 |
+
"VH": 2,
|
95 |
+
"VHC": 14,
|
96 |
+
"VI": 87,
|
97 |
+
"VJ": 16,
|
98 |
+
"VK": 6,
|
99 |
+
"VL": 17,
|
100 |
+
"V_2": 24,
|
101 |
+
"Vc": 65,
|
102 |
+
"Ve": 71,
|
103 |
+
"Vf": 84,
|
104 |
+
"Vg": 67,
|
105 |
+
"V\uff3f\uff12": 69,
|
106 |
+
"b": 44,
|
107 |
+
"na": 75,
|
108 |
+
"nc": 83,
|
109 |
+
"neu": 96,
|
110 |
+
"r": 73,
|
111 |
+
"\u7b26\uff0c\u5c1a\u7121\u8cc7\u6599": 68
|
112 |
+
},
|
113 |
+
"initializer_range": 0.02,
|
114 |
+
"intermediate_size": 3072,
|
115 |
+
"id2label": {
|
116 |
+
"0": "Na",
|
117 |
+
"1": "PERIODCATEGORY",
|
118 |
+
"2": "VH",
|
119 |
+
"3": "VC",
|
120 |
+
"4": "Nh",
|
121 |
+
"5": "VE",
|
122 |
+
"6": "VK",
|
123 |
+
"7": "Nc",
|
124 |
+
"8": "Neu",
|
125 |
+
"9": "Nb",
|
126 |
+
"10": "P",
|
127 |
+
"11": "Nd",
|
128 |
+
"12": "Dc",
|
129 |
+
"13": "VCL",
|
130 |
+
"14": "VHC",
|
131 |
+
"15": "T8",
|
132 |
+
"16": "VJ",
|
133 |
+
"17": "VL",
|
134 |
+
"18": "Dl",
|
135 |
+
"19": "Dd",
|
136 |
+
"20": "Cbb",
|
137 |
+
"21": "VG",
|
138 |
+
"22": "Ng",
|
139 |
+
"23": "VA",
|
140 |
+
"24": "V_2",
|
141 |
+
"25": "Nes",
|
142 |
+
"26": "T",
|
143 |
+
"27": "Dh",
|
144 |
+
"28": "Dab",
|
145 |
+
"29": "DE",
|
146 |
+
"30": "VAC",
|
147 |
+
"31": "Neqa",
|
148 |
+
"32": "COMMACATEGORY",
|
149 |
+
"33": "Nf",
|
150 |
+
"34": "Caa",
|
151 |
+
"35": "VD",
|
152 |
+
"36": "VF",
|
153 |
+
"37": "Dfa",
|
154 |
+
"38": "SHI",
|
155 |
+
"39": "Dj",
|
156 |
+
"40": "Daa",
|
157 |
+
"41": "A",
|
158 |
+
"42": "T6",
|
159 |
+
"43": "Dbb",
|
160 |
+
"44": "b",
|
161 |
+
"45": "Dba",
|
162 |
+
"46": "T5",
|
163 |
+
"47": "R",
|
164 |
+
"48": "QUESTIONCATEGORY",
|
165 |
+
"49": "COLONCATEGORY",
|
166 |
+
"50": "EXCLAMATIONCATEGORY",
|
167 |
+
"51": "PARENTHESISCATEGORY",
|
168 |
+
"52": "Dk",
|
169 |
+
"53": "571",
|
170 |
+
"54": "T7",
|
171 |
+
"55": "SEMICOLONCATEGORY",
|
172 |
+
"56": "DASHCATEGORY",
|
173 |
+
"57": "I",
|
174 |
+
"58": "PAUSECATEGORY",
|
175 |
+
"59": "Dfb",
|
176 |
+
"60": "U",
|
177 |
+
"61": "Dg",
|
178 |
+
"62": "Q",
|
179 |
+
"63": "VB",
|
180 |
+
"64": "FW",
|
181 |
+
"65": "Vc",
|
182 |
+
"66": "T4",
|
183 |
+
"67": "Vg",
|
184 |
+
"68": "\u7b26\uff0c\u5c1a\u7121\u8cc7\u6599",
|
185 |
+
"69": "V\uff3f\uff12",
|
186 |
+
"70": "NH",
|
187 |
+
"71": "Ve",
|
188 |
+
"72": "V",
|
189 |
+
"73": "r",
|
190 |
+
"74": "D",
|
191 |
+
"75": "na",
|
192 |
+
"76": "ND",
|
193 |
+
"77": "NB",
|
194 |
+
"78": "N",
|
195 |
+
"79": "EXCLANATIONCATEGORY",
|
196 |
+
"80": "DFa",
|
197 |
+
"81": "Di",
|
198 |
+
"82": "T3",
|
199 |
+
"83": "nc",
|
200 |
+
"84": "Vf",
|
201 |
+
"85": "Ne",
|
202 |
+
"86": "C",
|
203 |
+
"87": "VI",
|
204 |
+
"88": "DH",
|
205 |
+
"89": "Da",
|
206 |
+
"90": "PARENTHES7ISCATEGORY",
|
207 |
+
"91": "DJ",
|
208 |
+
"92": "DAb",
|
209 |
+
"93": "NA",
|
210 |
+
"94": "Df",
|
211 |
+
"95": "Db",
|
212 |
+
"96": "neu",
|
213 |
+
"97": "DC"
|
214 |
+
},
|
215 |
+
"layer_norm_eps": 1e-12,
|
216 |
+
"max_position_embeddings": 512,
|
217 |
+
"model_type": "bert",
|
218 |
+
"num_attention_heads": 12,
|
219 |
+
"num_hidden_layers": 12,
|
220 |
+
"pad_token_id": 0,
|
221 |
+
"pooler_fc_size": 768,
|
222 |
+
"pooler_num_attention_heads": 12,
|
223 |
+
"pooler_num_fc_layers": 3,
|
224 |
+
"pooler_size_per_head": 128,
|
225 |
+
"pooler_type": "first_token_transform",
|
226 |
+
"position_embedding_type": "absolute",
|
227 |
+
"tokenizer_class": "BertTokenizerFast",
|
228 |
+
"transformers_version": "4.7.0",
|
229 |
+
"type_vocab_size": 2,
|
230 |
+
"use_cache": true,
|
231 |
+
"vocab_size": 26140
|
232 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09e46de4be93e99b3e3068b00906adc50e6c7c3f5aeb742ab282ca9730bd7349
|
3 |
+
size 422458267
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
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, "model_max_length": 512, "name_or_path": "hub/ckiplab/bert-base-chinese-20210817-001848", "special_tokens_map_file": "/home/cindy666/.cache/huggingface/transformers/d8a1a1b7a3de221ae53bf9d55154b9df9c4cda18409b393ee0fda4bce4ca7818.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "do_basic_tokenize": true, "never_split": null}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|