Upload model files.
Browse files- README.md +19 -0
- config.json +176 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
datasets:
|
12 |
+
metrics:
|
13 |
+
---
|
14 |
+
|
15 |
+
# CKIP BERT Base Chinese β Named-Entity Recognition
|
16 |
+
|
17 |
+
## Contributers
|
18 |
+
|
19 |
+
* [Mu Yang](https://muyang.pro) at [CKIP](https://ckip.iis.sinica.edu.tw) (Author & Maintainer)
|
config.json
ADDED
@@ -0,0 +1,176 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BertForTokenClassification"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"directionality": "bidi",
|
7 |
+
"gradient_checkpointing": false,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "O",
|
13 |
+
"1": "B-CARDINAL",
|
14 |
+
"2": "B-DATE",
|
15 |
+
"3": "B-EVENT",
|
16 |
+
"4": "B-FAC",
|
17 |
+
"5": "B-GPE",
|
18 |
+
"6": "B-LANGUAGE",
|
19 |
+
"7": "B-LAW",
|
20 |
+
"8": "B-LOC",
|
21 |
+
"9": "B-MONEY",
|
22 |
+
"10": "B-NORP",
|
23 |
+
"11": "B-ORDINAL",
|
24 |
+
"12": "B-ORG",
|
25 |
+
"13": "B-PERCENT",
|
26 |
+
"14": "B-PERSON",
|
27 |
+
"15": "B-PRODUCT",
|
28 |
+
"16": "B-QUANTITY",
|
29 |
+
"17": "B-TIME",
|
30 |
+
"18": "B-WORK_OF_ART",
|
31 |
+
"19": "I-CARDINAL",
|
32 |
+
"20": "I-DATE",
|
33 |
+
"21": "I-EVENT",
|
34 |
+
"22": "I-FAC",
|
35 |
+
"23": "I-GPE",
|
36 |
+
"24": "I-LANGUAGE",
|
37 |
+
"25": "I-LAW",
|
38 |
+
"26": "I-LOC",
|
39 |
+
"27": "I-MONEY",
|
40 |
+
"28": "I-NORP",
|
41 |
+
"29": "I-ORDINAL",
|
42 |
+
"30": "I-ORG",
|
43 |
+
"31": "I-PERCENT",
|
44 |
+
"32": "I-PERSON",
|
45 |
+
"33": "I-PRODUCT",
|
46 |
+
"34": "I-QUANTITY",
|
47 |
+
"35": "I-TIME",
|
48 |
+
"36": "I-WORK_OF_ART",
|
49 |
+
"37": "E-CARDINAL",
|
50 |
+
"38": "E-DATE",
|
51 |
+
"39": "E-EVENT",
|
52 |
+
"40": "E-FAC",
|
53 |
+
"41": "E-GPE",
|
54 |
+
"42": "E-LANGUAGE",
|
55 |
+
"43": "E-LAW",
|
56 |
+
"44": "E-LOC",
|
57 |
+
"45": "E-MONEY",
|
58 |
+
"46": "E-NORP",
|
59 |
+
"47": "E-ORDINAL",
|
60 |
+
"48": "E-ORG",
|
61 |
+
"49": "E-PERCENT",
|
62 |
+
"50": "E-PERSON",
|
63 |
+
"51": "E-PRODUCT",
|
64 |
+
"52": "E-QUANTITY",
|
65 |
+
"53": "E-TIME",
|
66 |
+
"54": "E-WORK_OF_ART",
|
67 |
+
"55": "S-CARDINAL",
|
68 |
+
"56": "S-DATE",
|
69 |
+
"57": "S-EVENT",
|
70 |
+
"58": "S-FAC",
|
71 |
+
"59": "S-GPE",
|
72 |
+
"60": "S-LANGUAGE",
|
73 |
+
"61": "S-LAW",
|
74 |
+
"62": "S-LOC",
|
75 |
+
"63": "S-MONEY",
|
76 |
+
"64": "S-NORP",
|
77 |
+
"65": "S-ORDINAL",
|
78 |
+
"66": "S-ORG",
|
79 |
+
"67": "S-PERCENT",
|
80 |
+
"68": "S-PERSON",
|
81 |
+
"69": "S-PRODUCT",
|
82 |
+
"70": "S-QUANTITY",
|
83 |
+
"71": "S-TIME",
|
84 |
+
"72": "S-WORK_OF_ART"
|
85 |
+
},
|
86 |
+
"initializer_range": 0.02,
|
87 |
+
"intermediate_size": 3072,
|
88 |
+
"label2id": {
|
89 |
+
"B-CARDINAL": 1,
|
90 |
+
"B-DATE": 2,
|
91 |
+
"B-EVENT": 3,
|
92 |
+
"B-FAC": 4,
|
93 |
+
"B-GPE": 5,
|
94 |
+
"B-LANGUAGE": 6,
|
95 |
+
"B-LAW": 7,
|
96 |
+
"B-LOC": 8,
|
97 |
+
"B-MONEY": 9,
|
98 |
+
"B-NORP": 10,
|
99 |
+
"B-ORDINAL": 11,
|
100 |
+
"B-ORG": 12,
|
101 |
+
"B-PERCENT": 13,
|
102 |
+
"B-PERSON": 14,
|
103 |
+
"B-PRODUCT": 15,
|
104 |
+
"B-QUANTITY": 16,
|
105 |
+
"B-TIME": 17,
|
106 |
+
"B-WORK_OF_ART": 18,
|
107 |
+
"E-CARDINAL": 37,
|
108 |
+
"E-DATE": 38,
|
109 |
+
"E-EVENT": 39,
|
110 |
+
"E-FAC": 40,
|
111 |
+
"E-GPE": 41,
|
112 |
+
"E-LANGUAGE": 42,
|
113 |
+
"E-LAW": 43,
|
114 |
+
"E-LOC": 44,
|
115 |
+
"E-MONEY": 45,
|
116 |
+
"E-NORP": 46,
|
117 |
+
"E-ORDINAL": 47,
|
118 |
+
"E-ORG": 48,
|
119 |
+
"E-PERCENT": 49,
|
120 |
+
"E-PERSON": 50,
|
121 |
+
"E-PRODUCT": 51,
|
122 |
+
"E-QUANTITY": 52,
|
123 |
+
"E-TIME": 53,
|
124 |
+
"E-WORK_OF_ART": 54,
|
125 |
+
"I-CARDINAL": 19,
|
126 |
+
"I-DATE": 20,
|
127 |
+
"I-EVENT": 21,
|
128 |
+
"I-FAC": 22,
|
129 |
+
"I-GPE": 23,
|
130 |
+
"I-LANGUAGE": 24,
|
131 |
+
"I-LAW": 25,
|
132 |
+
"I-LOC": 26,
|
133 |
+
"I-MONEY": 27,
|
134 |
+
"I-NORP": 28,
|
135 |
+
"I-ORDINAL": 29,
|
136 |
+
"I-ORG": 30,
|
137 |
+
"I-PERCENT": 31,
|
138 |
+
"I-PERSON": 32,
|
139 |
+
"I-PRODUCT": 33,
|
140 |
+
"I-QUANTITY": 34,
|
141 |
+
"I-TIME": 35,
|
142 |
+
"I-WORK_OF_ART": 36,
|
143 |
+
"O": 0,
|
144 |
+
"S-CARDINAL": 55,
|
145 |
+
"S-DATE": 56,
|
146 |
+
"S-EVENT": 57,
|
147 |
+
"S-FAC": 58,
|
148 |
+
"S-GPE": 59,
|
149 |
+
"S-LANGUAGE": 60,
|
150 |
+
"S-LAW": 61,
|
151 |
+
"S-LOC": 62,
|
152 |
+
"S-MONEY": 63,
|
153 |
+
"S-NORP": 64,
|
154 |
+
"S-ORDINAL": 65,
|
155 |
+
"S-ORG": 66,
|
156 |
+
"S-PERCENT": 67,
|
157 |
+
"S-PERSON": 68,
|
158 |
+
"S-PRODUCT": 69,
|
159 |
+
"S-QUANTITY": 70,
|
160 |
+
"S-TIME": 71,
|
161 |
+
"S-WORK_OF_ART": 72
|
162 |
+
},
|
163 |
+
"layer_norm_eps": 1e-12,
|
164 |
+
"max_position_embeddings": 512,
|
165 |
+
"model_type": "bert",
|
166 |
+
"num_attention_heads": 12,
|
167 |
+
"num_hidden_layers": 12,
|
168 |
+
"pad_token_id": 0,
|
169 |
+
"pooler_fc_size": 768,
|
170 |
+
"pooler_num_attention_heads": 12,
|
171 |
+
"pooler_num_fc_layers": 3,
|
172 |
+
"pooler_size_per_head": 128,
|
173 |
+
"pooler_type": "first_token_transform",
|
174 |
+
"type_vocab_size": 2,
|
175 |
+
"vocab_size": 21128
|
176 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f63373ccef4de549747b36a267f81eea553ecfa3476e2726ad689e430ddff491
|
3 |
+
size 407021303
|
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_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": false, "do_basic_tokenize": true, "never_split": null, "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": "bert-base-chinese"}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|