emfomy commited on
Commit
32e9948
β€’
1 Parent(s): f6a3ba0

Upload model files.

Browse files
Files changed (6) hide show
  1. README.md +22 -0
  2. config.json +180 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +1 -0
  5. tokenizer_config.json +1 -0
  6. vocab.txt +0 -0
README.md ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ - albert
9
+ - zh
10
+ license: gpl-3.0
11
+ datasets:
12
+ metrics:
13
+ ---
14
+
15
+ # CKIP ALBERT 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)
20
+
21
+ ## Attention
22
+ Please Use `BertTokenizer` instead of `AutoTokenizer`!!!
config.json ADDED
@@ -0,0 +1,180 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "AlbertForTokenClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0,
6
+ "bos_token_id": 2,
7
+ "classifier_dropout_prob": 0.1,
8
+ "down_scale_factor": 1,
9
+ "embedding_size": 128,
10
+ "eos_token_id": 3,
11
+ "gap_size": 0,
12
+ "hidden_act": "relu",
13
+ "hidden_dropout_prob": 0,
14
+ "hidden_size": 768,
15
+ "id2label": {
16
+ "0": "O",
17
+ "1": "B-CARDINAL",
18
+ "2": "B-DATE",
19
+ "3": "B-EVENT",
20
+ "4": "B-FAC",
21
+ "5": "B-GPE",
22
+ "6": "B-LANGUAGE",
23
+ "7": "B-LAW",
24
+ "8": "B-LOC",
25
+ "9": "B-MONEY",
26
+ "10": "B-NORP",
27
+ "11": "B-ORDINAL",
28
+ "12": "B-ORG",
29
+ "13": "B-PERCENT",
30
+ "14": "B-PERSON",
31
+ "15": "B-PRODUCT",
32
+ "16": "B-QUANTITY",
33
+ "17": "B-TIME",
34
+ "18": "B-WORK_OF_ART",
35
+ "19": "I-CARDINAL",
36
+ "20": "I-DATE",
37
+ "21": "I-EVENT",
38
+ "22": "I-FAC",
39
+ "23": "I-GPE",
40
+ "24": "I-LANGUAGE",
41
+ "25": "I-LAW",
42
+ "26": "I-LOC",
43
+ "27": "I-MONEY",
44
+ "28": "I-NORP",
45
+ "29": "I-ORDINAL",
46
+ "30": "I-ORG",
47
+ "31": "I-PERCENT",
48
+ "32": "I-PERSON",
49
+ "33": "I-PRODUCT",
50
+ "34": "I-QUANTITY",
51
+ "35": "I-TIME",
52
+ "36": "I-WORK_OF_ART",
53
+ "37": "E-CARDINAL",
54
+ "38": "E-DATE",
55
+ "39": "E-EVENT",
56
+ "40": "E-FAC",
57
+ "41": "E-GPE",
58
+ "42": "E-LANGUAGE",
59
+ "43": "E-LAW",
60
+ "44": "E-LOC",
61
+ "45": "E-MONEY",
62
+ "46": "E-NORP",
63
+ "47": "E-ORDINAL",
64
+ "48": "E-ORG",
65
+ "49": "E-PERCENT",
66
+ "50": "E-PERSON",
67
+ "51": "E-PRODUCT",
68
+ "52": "E-QUANTITY",
69
+ "53": "E-TIME",
70
+ "54": "E-WORK_OF_ART",
71
+ "55": "S-CARDINAL",
72
+ "56": "S-DATE",
73
+ "57": "S-EVENT",
74
+ "58": "S-FAC",
75
+ "59": "S-GPE",
76
+ "60": "S-LANGUAGE",
77
+ "61": "S-LAW",
78
+ "62": "S-LOC",
79
+ "63": "S-MONEY",
80
+ "64": "S-NORP",
81
+ "65": "S-ORDINAL",
82
+ "66": "S-ORG",
83
+ "67": "S-PERCENT",
84
+ "68": "S-PERSON",
85
+ "69": "S-PRODUCT",
86
+ "70": "S-QUANTITY",
87
+ "71": "S-TIME",
88
+ "72": "S-WORK_OF_ART"
89
+ },
90
+ "initializer_range": 0.02,
91
+ "inner_group_num": 1,
92
+ "intermediate_size": 3072,
93
+ "label2id": {
94
+ "B-CARDINAL": 1,
95
+ "B-DATE": 2,
96
+ "B-EVENT": 3,
97
+ "B-FAC": 4,
98
+ "B-GPE": 5,
99
+ "B-LANGUAGE": 6,
100
+ "B-LAW": 7,
101
+ "B-LOC": 8,
102
+ "B-MONEY": 9,
103
+ "B-NORP": 10,
104
+ "B-ORDINAL": 11,
105
+ "B-ORG": 12,
106
+ "B-PERCENT": 13,
107
+ "B-PERSON": 14,
108
+ "B-PRODUCT": 15,
109
+ "B-QUANTITY": 16,
110
+ "B-TIME": 17,
111
+ "B-WORK_OF_ART": 18,
112
+ "E-CARDINAL": 37,
113
+ "E-DATE": 38,
114
+ "E-EVENT": 39,
115
+ "E-FAC": 40,
116
+ "E-GPE": 41,
117
+ "E-LANGUAGE": 42,
118
+ "E-LAW": 43,
119
+ "E-LOC": 44,
120
+ "E-MONEY": 45,
121
+ "E-NORP": 46,
122
+ "E-ORDINAL": 47,
123
+ "E-ORG": 48,
124
+ "E-PERCENT": 49,
125
+ "E-PERSON": 50,
126
+ "E-PRODUCT": 51,
127
+ "E-QUANTITY": 52,
128
+ "E-TIME": 53,
129
+ "E-WORK_OF_ART": 54,
130
+ "I-CARDINAL": 19,
131
+ "I-DATE": 20,
132
+ "I-EVENT": 21,
133
+ "I-FAC": 22,
134
+ "I-GPE": 23,
135
+ "I-LANGUAGE": 24,
136
+ "I-LAW": 25,
137
+ "I-LOC": 26,
138
+ "I-MONEY": 27,
139
+ "I-NORP": 28,
140
+ "I-ORDINAL": 29,
141
+ "I-ORG": 30,
142
+ "I-PERCENT": 31,
143
+ "I-PERSON": 32,
144
+ "I-PRODUCT": 33,
145
+ "I-QUANTITY": 34,
146
+ "I-TIME": 35,
147
+ "I-WORK_OF_ART": 36,
148
+ "O": 0,
149
+ "S-CARDINAL": 55,
150
+ "S-DATE": 56,
151
+ "S-EVENT": 57,
152
+ "S-FAC": 58,
153
+ "S-GPE": 59,
154
+ "S-LANGUAGE": 60,
155
+ "S-LAW": 61,
156
+ "S-LOC": 62,
157
+ "S-MONEY": 63,
158
+ "S-NORP": 64,
159
+ "S-ORDINAL": 65,
160
+ "S-ORG": 66,
161
+ "S-PERCENT": 67,
162
+ "S-PERSON": 68,
163
+ "S-PRODUCT": 69,
164
+ "S-QUANTITY": 70,
165
+ "S-TIME": 71,
166
+ "S-WORK_OF_ART": 72
167
+ },
168
+ "layer_norm_eps": 1e-12,
169
+ "layers_to_keep": [],
170
+ "max_position_embeddings": 512,
171
+ "model_type": "albert",
172
+ "net_structure_type": 0,
173
+ "num_attention_heads": 12,
174
+ "num_hidden_groups": 1,
175
+ "num_hidden_layers": 12,
176
+ "num_memory_blocks": 0,
177
+ "pad_token_id": 0,
178
+ "type_vocab_size": 2,
179
+ "vocab_size": 21128
180
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa85a21f1e8e9d70fec279db92eba51c4438491dba68092057f2583f9b173f50
3
+ size 40069401
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